TaskFlow
DashboardFreewriteWhiteboardsProjectsCRMTasksNotificationsSettingsAgent TowerAPI Docs
OpenClaw Docs
?

User

Member

Caricamento in corso...

Home
Progetti
Task
Notifiche
CRM

    OpenClaw

    Documentation Mirror

    Documentation Overview

    Docs

    Auth credential semantics
    Scheduled tasks
    Hooks
    Automation & tasks
    Standing orders
    Task flow
    Background tasks
    BlueBubbles
    Broadcast groups
    Channel routing
    Discord
    Feishu
    Google Chat
    Group messages
    Groups
    iMessage
    Chat channels
    IRC
    LINE
    Channel location parsing
    Matrix
    Matrix migration
    Matrix push rules for quiet previews
    Mattermost
    Microsoft Teams
    Nextcloud Talk
    Nostr
    Pairing
    QA channel
    QQ bot
    Signal
    Slack
    Synology Chat
    Telegram
    Tlon
    Channel troubleshooting
    Twitch
    WeChat
    WhatsApp
    Yuanbao
    Zalo
    Zalo personal
    CI pipeline
    ACP
    Agent
    Agents
    Approvals
    Backup
    Browser
    Channels
    Clawbot
    `openclaw commitments`
    Completion
    Config
    Configure
    Cron
    Daemon
    Dashboard
    Devices
    Directory
    DNS
    Docs
    Doctor
    Flows (redirect)
    Gateway
    Health
    Hooks
    CLI reference
    Inference CLI
    Logs
    MCP
    Memory
    Message
    Migrate
    Models
    Node
    Nodes
    Onboard
    Pairing
    Plugins
    Proxy
    QR
    Reset
    Sandbox CLI
    Secrets
    Security
    Sessions
    Setup
    Skills
    Status
    System
    `openclaw tasks`
    TUI
    Uninstall
    Update
    Voicecall
    Webhooks
    Wiki
    Active memory
    Agent runtime
    Agent loop
    Agent runtimes
    Agent workspace
    Gateway architecture
    Channel docking
    Inferred commitments
    Compaction
    Context
    Context engine
    Delegate architecture
    Dreaming
    Experimental features
    Features
    Markdown formatting
    Memory overview
    Builtin memory engine
    Honcho memory
    QMD memory engine
    Memory search
    Messages
    Model failover
    Model providers
    Models CLI
    Multi-agent routing
    OAuth
    OpenClaw App SDK
    Presence
    QA overview
    Matrix QA
    Command queue
    Steering queue
    Retry policy
    Session management
    Session pruning
    Session tools
    SOUL.md personality guide
    Streaming and chunking
    System prompt
    Timezones
    TypeBox
    Typing indicators
    Usage tracking
    Date and time
    Node + tsx crash
    Diagnostics flags
    Authentication
    Background exec and process tool
    Bonjour discovery
    Bridge protocol
    CLI backends
    Configuration — agents
    Configuration — channels
    Configuration — tools and custom providers
    Configuration
    Configuration examples
    Configuration reference
    Diagnostics export
    Discovery and transports
    Doctor
    Gateway lock
    Health checks
    Heartbeat
    Gateway runbook
    Local models
    Gateway logging
    Multiple gateways
    Network model
    OpenAI chat completions
    OpenResponses API
    OpenShell
    OpenTelemetry export
    Gateway-owned pairing
    Prometheus metrics
    Gateway protocol
    Remote access
    Remote gateway setup
    Sandbox vs tool policy vs elevated
    Sandboxing
    Secrets management
    Secrets apply plan contract
    Security audit checks
    Security
    Tailscale
    Tools invoke API
    Troubleshooting
    Trusted proxy auth
    Debugging
    Environment variables
    FAQ
    FAQ: first-run setup
    FAQ: models and auth
    GPT-5.5 / Codex agentic parity
    GPT-5.5 / Codex parity maintainer notes
    Help
    Scripts
    Testing
    Testing: live suites
    General troubleshooting
    OpenClaw
    Ansible
    Azure
    Bun (experimental)
    ClawDock
    Release channels
    DigitalOcean
    Docker
    Docker VM runtime
    exe.dev
    Fly.io
    GCP
    Hetzner
    Hostinger
    Install
    Installer internals
    Kubernetes
    macOS VMs
    Migration guide
    Migrating from Claude
    Migrating from Hermes
    Nix
    Node.js
    Northflank
    Oracle Cloud
    Podman
    Railway
    Raspberry Pi
    Render
    Uninstall
    Updating
    Logging
    Network
    Audio and voice notes
    Camera capture
    Image and media support
    Nodes
    Location command
    Media understanding
    Talk mode
    Node troubleshooting
    Voice wake
    Pi integration architecture
    Pi development workflow
    Android app
    Platforms
    iOS app
    Linux app
    Gateway on macOS
    Canvas
    Gateway lifecycle
    macOS dev setup
    Health checks (macOS)
    Menu bar icon
    macOS logging
    Menu bar
    Peekaboo bridge
    macOS permissions
    Remote control
    macOS signing
    Skills (macOS)
    Voice overlay
    Voice wake (macOS)
    WebChat (macOS)
    macOS IPC
    macOS app
    Windows
    Plugin internals
    Plugin architecture internals
    Building plugins
    Plugin bundles
    Codex Computer Use
    Codex harness
    Community plugins
    Plugin compatibility
    Google Meet plugin
    Plugin hooks
    Plugin manifest
    Memory LanceDB
    Memory wiki
    Message presentation
    Agent harness plugins
    Building channel plugins
    Channel turn kernel
    Plugin entry points
    Plugin SDK migration
    Plugin SDK overview
    Building provider plugins
    Plugin runtime helpers
    Plugin setup and config
    Plugin SDK subpaths
    Plugin testing
    Skill workshop plugin
    Voice call plugin
    Webhooks plugin
    Zalo personal plugin
    OpenProse
    Alibaba Model Studio
    Anthropic
    Arcee AI
    Azure Speech
    Amazon Bedrock
    Amazon Bedrock Mantle
    Chutes
    Claude Max API proxy
    Cloudflare AI gateway
    ComfyUI
    Deepgram
    Deepinfra
    DeepSeek
    ElevenLabs
    Fal
    Fireworks
    GitHub Copilot
    GLM (Zhipu)
    Google (Gemini)
    Gradium
    Groq
    Hugging Face (inference)
    Provider directory
    Inferrs
    Inworld
    Kilocode
    LiteLLM
    LM Studio
    MiniMax
    Mistral
    Model provider quickstart
    Moonshot AI
    NVIDIA
    Ollama
    OpenAI
    OpenCode
    OpenCode Go
    OpenRouter
    Perplexity
    Qianfan
    Qwen
    Runway
    SGLang
    StepFun
    Synthetic
    Tencent Cloud (TokenHub)
    Together AI
    Venice AI
    Vercel AI gateway
    vLLM
    Volcengine (Doubao)
    Vydra
    xAI
    Xiaomi MiMo
    Z.AI
    Default AGENTS.md
    Release policy
    API usage and costs
    Credits
    Device model database
    Full release validation
    Memory configuration reference
    OpenClaw App SDK API design
    Prompt caching
    Rich output protocol
    RPC adapters
    SecretRef credential surface
    Session management deep dive
    AGENTS.md template
    BOOT.md template
    BOOTSTRAP.md template
    HEARTBEAT.md template
    IDENTITY template
    SOUL.md template
    TOOLS.md template
    USER template
    Tests
    Token use and costs
    Transcript hygiene
    Onboarding reference
    Contributing to the threat model
    Threat model (MITRE ATLAS)
    Formal verification (security models)
    Network proxy
    Agent bootstrapping
    Docs directory
    Getting started
    Docs hubs
    OpenClaw lore
    Onboarding (macOS app)
    Onboarding overview
    Personal assistant setup
    Setup
    Showcase
    Onboarding (CLI)
    CLI automation
    CLI setup reference
    ACP agents
    ACP agents — setup
    Agent send
    apply_patch tool
    Brave search
    Browser (OpenClaw-managed)
    Browser control API
    Browser troubleshooting
    Browser login
    WSL2 + Windows + remote Chrome CDP troubleshooting
    BTW side questions
    ClawHub
    Code execution
    Creating skills
    Diffs
    DuckDuckGo search
    Elevated mode
    Exa search
    Exec tool
    Exec approvals
    Exec approvals — advanced
    Firecrawl
    Gemini search
    Grok search
    Image generation
    Tools and plugins
    Kimi search
    LLM task
    Lobster
    Tool-loop detection
    Media overview
    MiniMax search
    Multi-agent sandbox and tools
    Music generation
    Ollama web search
    PDF tool
    Perplexity search
    Plugins
    Reactions
    SearXNG search
    Skills
    Skills config
    Slash commands
    Sub-agents
    Tavily
    Thinking levels
    Tokenjuice
    Trajectory bundles
    Text-to-speech
    Video generation
    Web search
    Web fetch
    Linux server
    Control UI
    Dashboard
    Web
    TUI
    WebChat

    OpenAPI Specs

    openapi
    TaskFlow
    docs/openclaw
    Original Docs

    Real-time Synchronized Documentation

    Last sync: 01/05/2026 07:05:24

    Note: This content is mirrored from docs.openclaw.ai and is subject to their terms and conditions.

    OpenClaw Docs

    v2.4.0 Production

    Last synced: Today, 22:00

    Technical reference for the OpenClaw framework. Real-time synchronization with the official documentation engine.

    Use this file to discover all available pages before exploring further.

    Security audit checks

    text
    openclaw security audit
    emits structured findings keyed by
    text
    checkId
    . This page is the reference catalog for those IDs. For the high-level threat model and hardening guidance, see Security.

    High-signal

    text
    checkId
    values you will most likely see in real deployments (not exhaustive):

    text
    checkId
    SeverityWhy it mattersPrimary fix key/pathAuto-fix
    text
    fs.state_dir.perms_world_writable
    criticalOther users/processes can modify full OpenClaw statefilesystem perms on
    text
    ~/.openclaw
    yes
    text
    fs.state_dir.perms_group_writable
    warnGroup users can modify full OpenClaw statefilesystem perms on
    text
    ~/.openclaw
    yes
    text
    fs.state_dir.perms_readable
    warnState dir is readable by othersfilesystem perms on
    text
    ~/.openclaw
    yes
    text
    fs.state_dir.symlink
    warnState dir target becomes another trust boundarystate dir filesystem layoutno
    text
    fs.config.perms_writable
    criticalOthers can change auth/tool policy/configfilesystem perms on
    text
    ~/.openclaw/openclaw.json
    yes
    text
    fs.config.symlink
    warnSymlinked config files are unsupported for writes and add another trust boundaryreplace with a regular config file or point
    text
    OPENCLAW_CONFIG_PATH
    at the real file
    no
    text
    fs.config.perms_group_readable
    warnGroup users can read config tokens/settingsfilesystem perms on config fileyes
    text
    fs.config.perms_world_readable
    criticalConfig can expose tokens/settingsfilesystem perms on config fileyes
    text
    fs.config_include.perms_writable
    criticalConfig include file can be modified by othersinclude-file perms referenced from
    text
    openclaw.json
    yes
    text
    fs.config_include.perms_group_readable
    warnGroup users can read included secrets/settingsinclude-file perms referenced from
    text
    openclaw.json
    yes
    text
    fs.config_include.perms_world_readable
    criticalIncluded secrets/settings are world-readableinclude-file perms referenced from
    text
    openclaw.json
    yes
    text
    fs.auth_profiles.perms_writable
    criticalOthers can inject or replace stored model credentials
    text
    agents/<agentId>/agent/auth-profiles.json
    perms
    yes
    text
    fs.auth_profiles.perms_readable
    warnOthers can read API keys and OAuth tokens
    text
    agents/<agentId>/agent/auth-profiles.json
    perms
    yes
    text
    fs.credentials_dir.perms_writable
    criticalOthers can modify channel pairing/credential statefilesystem perms on
    text
    ~/.openclaw/credentials
    yes
    text
    fs.credentials_dir.perms_readable
    warnOthers can read channel credential statefilesystem perms on
    text
    ~/.openclaw/credentials
    yes
    text
    fs.sessions_store.perms_readable
    warnOthers can read session transcripts/metadatasession store permsyes
    text
    fs.log_file.perms_readable
    warnOthers can read redacted-but-still-sensitive logsgateway log file permsyes
    text
    fs.synced_dir
    warnState/config in iCloud/Dropbox/Drive broadens token/transcript exposuremove config/state off synced foldersno
    text
    gateway.bind_no_auth
    criticalRemote bind without shared secret
    text
    gateway.bind
    ,
    text
    gateway.auth.*
    no
    text
    gateway.loopback_no_auth
    criticalReverse-proxied loopback may become unauthenticated
    text
    gateway.auth.*
    , proxy setup
    no
    text
    gateway.trusted_proxies_missing
    warnReverse-proxy headers are present but not trusted
    text
    gateway.trustedProxies
    no
    text
    gateway.http.no_auth
    warn/criticalGateway HTTP APIs reachable with
    text
    auth.mode="none"
    text
    gateway.auth.mode
    ,
    text
    gateway.http.endpoints.*
    no
    text
    gateway.http.session_key_override_enabled
    infoHTTP API callers can override
    text
    sessionKey
    text
    gateway.http.allowSessionKeyOverride
    no
    text
    gateway.tools_invoke_http.dangerous_allow
    warn/criticalRe-enables dangerous tools over HTTP API
    text
    gateway.tools.allow
    no
    text
    gateway.nodes.allow_commands_dangerous
    warn/criticalEnables high-impact node commands (camera/screen/contacts/calendar/SMS)
    text
    gateway.nodes.allowCommands
    no
    text
    gateway.nodes.deny_commands_ineffective
    warnPattern-like deny entries do not match shell text or groups
    text
    gateway.nodes.denyCommands
    no
    text
    gateway.tailscale_funnel
    criticalPublic internet exposure
    text
    gateway.tailscale.mode
    no
    text
    gateway.tailscale_serve
    infoTailnet exposure is enabled via Serve
    text
    gateway.tailscale.mode
    no
    text
    gateway.control_ui.allowed_origins_required
    criticalNon-loopback Control UI without explicit browser-origin allowlist
    text
    gateway.controlUi.allowedOrigins
    no
    text
    gateway.control_ui.allowed_origins_wildcard
    warn/critical
    text
    allowedOrigins=["*"]
    disables browser-origin allowlisting
    text
    gateway.controlUi.allowedOrigins
    no
    text
    gateway.control_ui.host_header_origin_fallback
    warn/criticalEnables Host-header origin fallback (DNS rebinding hardening downgrade)
    text
    gateway.controlUi.dangerouslyAllowHostHeaderOriginFallback
    no
    text
    gateway.control_ui.insecure_auth
    warnInsecure-auth compatibility toggle enabled
    text
    gateway.controlUi.allowInsecureAuth
    no
    text
    gateway.control_ui.device_auth_disabled
    criticalDisables device identity check
    text
    gateway.controlUi.dangerouslyDisableDeviceAuth
    no
    text
    gateway.real_ip_fallback_enabled
    warn/criticalTrusting
    text
    X-Real-IP
    fallback can enable source-IP spoofing via proxy misconfig
    text
    gateway.allowRealIpFallback
    ,
    text
    gateway.trustedProxies
    no
    text
    gateway.token_too_short
    warnShort shared token is easier to brute force
    text
    gateway.auth.token
    no
    text
    gateway.auth_no_rate_limit
    warnExposed auth without rate limiting increases brute-force risk
    text
    gateway.auth.rateLimit
    no
    text
    gateway.trusted_proxy_auth
    criticalProxy identity now becomes the auth boundary
    text
    gateway.auth.mode="trusted-proxy"
    no
    text
    gateway.trusted_proxy_no_proxies
    criticalTrusted-proxy auth without trusted proxy IPs is unsafe
    text
    gateway.trustedProxies
    no
    text
    gateway.trusted_proxy_no_user_header
    criticalTrusted-proxy auth cannot resolve user identity safely
    text
    gateway.auth.trustedProxy.userHeader
    no
    text
    gateway.trusted_proxy_no_allowlist
    warnTrusted-proxy auth accepts any authenticated upstream user
    text
    gateway.auth.trustedProxy.allowUsers
    no
    text
    gateway.trusted_proxy_allow_loopback
    warnTrusted-proxy auth accepts explicitly allowed loopback proxy sources
    text
    gateway.auth.trustedProxy.allowLoopback
    no
    text
    gateway.probe_auth_secretref_unavailable
    warnDeep probe could not resolve auth SecretRefs in this command pathdeep-probe auth source / SecretRef availabilityno
    text
    gateway.probe_failed
    warn/criticalLive Gateway probe failedgateway reachability/authno
    text
    discovery.mdns_full_mode
    warn/criticalmDNS full mode advertises
    text
    cliPath
    /
    text
    sshPort
    metadata on local network
    text
    discovery.mdns.mode
    ,
    text
    gateway.bind
    no
    text
    config.insecure_or_dangerous_flags
    warnAny insecure/dangerous debug flags enabledmultiple keys (see finding detail)no
    text
    config.secrets.gateway_password_in_config
    warnGateway password is stored directly in config
    text
    gateway.auth.password
    no
    text
    config.secrets.hooks_token_in_config
    warnHook bearer token is stored directly in config
    text
    hooks.token
    no
    text
    hooks.token_reuse_gateway_token
    criticalHook ingress token also unlocks Gateway auth
    text
    hooks.token
    ,
    text
    gateway.auth.token
    no
    text
    hooks.token_too_short
    warnEasier brute force on hook ingress
    text
    hooks.token
    no
    text
    hooks.default_session_key_unset
    warnHook agent runs fan out into generated per-request sessions
    text
    hooks.defaultSessionKey
    no
    text
    hooks.allowed_agent_ids_unrestricted
    warn/criticalAuthenticated hook callers may route to any configured agent
    text
    hooks.allowedAgentIds
    no
    text
    hooks.request_session_key_enabled
    warn/criticalExternal caller can choose sessionKey
    text
    hooks.allowRequestSessionKey
    no
    text
    hooks.request_session_key_prefixes_missing
    warn/criticalNo bound on external session key shapes
    text
    hooks.allowedSessionKeyPrefixes
    no
    text
    hooks.path_root
    criticalHook path is
    text
    /
    , making ingress easier to collide or misroute
    text
    hooks.path
    no
    text
    hooks.installs_unpinned_npm_specs
    warnHook install records are not pinned to immutable npm specshook install metadatano
    text
    hooks.installs_missing_integrity
    warnHook install records lack integrity metadatahook install metadatano
    text
    hooks.installs_version_drift
    warnHook install records drift from installed packageshook install metadatano
    text
    logging.redact_off
    warnSensitive values leak to logs/status
    text
    logging.redactSensitive
    yes
    text
    browser.control_invalid_config
    warnBrowser control config is invalid before runtime
    text
    browser.*
    no
    text
    browser.control_no_auth
    criticalBrowser control exposed without token/password auth
    text
    gateway.auth.*
    no
    text
    browser.remote_cdp_http
    warnRemote CDP over plain HTTP lacks transport encryptionbrowser profile
    text
    cdpUrl
    no
    text
    browser.remote_cdp_private_host
    warnRemote CDP targets a private/internal hostbrowser profile
    text
    cdpUrl
    ,
    text
    browser.ssrfPolicy.*
    no
    text
    sandbox.docker_config_mode_off
    warnSandbox Docker config present but inactive
    text
    agents.*.sandbox.mode
    no
    text
    sandbox.bind_mount_non_absolute
    warnRelative bind mounts can resolve unpredictably
    text
    agents.*.sandbox.docker.binds[]
    no
    text
    sandbox.dangerous_bind_mount
    criticalSandbox bind mount targets blocked system, credential, or Docker socket paths
    text
    agents.*.sandbox.docker.binds[]
    no
    text
    sandbox.dangerous_network_mode
    criticalSandbox Docker network uses
    text
    host
    or
    text
    container:*
    namespace-join mode
    text
    agents.*.sandbox.docker.network
    no
    text
    sandbox.dangerous_seccomp_profile
    criticalSandbox seccomp profile weakens container isolation
    text
    agents.*.sandbox.docker.securityOpt
    no
    text
    sandbox.dangerous_apparmor_profile
    criticalSandbox AppArmor profile weakens container isolation
    text
    agents.*.sandbox.docker.securityOpt
    no
    text
    sandbox.browser_cdp_bridge_unrestricted
    warnSandbox browser bridge is exposed without source-range restriction
    text
    sandbox.browser.cdpSourceRange
    no
    text
    sandbox.browser_container.non_loopback_publish
    criticalExisting browser container publishes CDP on non-loopback interfacesbrowser sandbox container publish configno
    text
    sandbox.browser_container.hash_label_missing
    warnExisting browser container predates current config-hash labels
    text
    openclaw sandbox recreate --browser --all
    no
    text
    sandbox.browser_container.hash_epoch_stale
    warnExisting browser container predates current browser config epoch
    text
    openclaw sandbox recreate --browser --all
    no
    text
    tools.exec.host_sandbox_no_sandbox_defaults
    warn
    text
    exec host=sandbox
    fails closed when sandbox is off
    text
    tools.exec.host
    ,
    text
    agents.defaults.sandbox.mode
    no
    text
    tools.exec.host_sandbox_no_sandbox_agents
    warnPer-agent
    text
    exec host=sandbox
    fails closed when sandbox is off
    text
    agents.list[].tools.exec.host
    ,
    text
    agents.list[].sandbox.mode
    no
    text
    tools.exec.security_full_configured
    warn/criticalHost exec is running with
    text
    security="full"
    text
    tools.exec.security
    ,
    text
    agents.list[].tools.exec.security
    no
    text
    tools.exec.auto_allow_skills_enabled
    warnExec approvals trust skill bins implicitly
    text
    ~/.openclaw/exec-approvals.json
    no
    text
    tools.exec.allowlist_interpreter_without_strict_inline_eval
    warnInterpreter allowlists permit inline eval without forced reapproval
    text
    tools.exec.strictInlineEval
    ,
    text
    agents.list[].tools.exec.strictInlineEval
    , exec approvals allowlist
    no
    text
    tools.exec.safe_bins_interpreter_unprofiled
    warnInterpreter/runtime bins in
    text
    safeBins
    without explicit profiles broaden exec risk
    text
    tools.exec.safeBins
    ,
    text
    tools.exec.safeBinProfiles
    ,
    text
    agents.list[].tools.exec.*
    no
    text
    tools.exec.safe_bins_broad_behavior
    warnBroad-behavior tools in
    text
    safeBins
    weaken the low-risk stdin-filter trust model
    text
    tools.exec.safeBins
    ,
    text
    agents.list[].tools.exec.safeBins
    no
    text
    tools.exec.safe_bin_trusted_dirs_risky
    warn
    text
    safeBinTrustedDirs
    includes mutable or risky directories
    text
    tools.exec.safeBinTrustedDirs
    ,
    text
    agents.list[].tools.exec.safeBinTrustedDirs
    no
    text
    skills.workspace.symlink_escape
    warnWorkspace
    text
    skills/**/SKILL.md
    resolves outside workspace root (symlink-chain drift)
    workspace
    text
    skills/**
    filesystem state
    no
    text
    plugins.extensions_no_allowlist
    warnPlugins are installed without an explicit plugin allowlist
    text
    plugins.allowlist
    no
    text
    plugins.installs_unpinned_npm_specs
    warnPlugin index records are not pinned to immutable npm specsplugin install metadatano
    text
    plugins.installs_missing_integrity
    warnPlugin index records lack integrity metadataplugin install metadatano
    text
    plugins.installs_version_drift
    warnPlugin index records drift from installed packagesplugin install metadatano
    text
    plugins.code_safety
    warn/criticalPlugin code scan found suspicious or dangerous patternsplugin code / install sourceno
    text
    plugins.code_safety.entry_path
    warnPlugin entry path points into hidden or
    text
    node_modules
    locations
    plugin manifest
    text
    entry
    no
    text
    plugins.code_safety.entry_escape
    criticalPlugin entry escapes the plugin directoryplugin manifest
    text
    entry
    no
    text
    plugins.code_safety.scan_failed
    warnPlugin code scan could not completeplugin path / scan environmentno
    text
    skills.code_safety
    warn/criticalSkill installer metadata/code contains suspicious or dangerous patternsskill install sourceno
    text
    skills.code_safety.scan_failed
    warnSkill code scan could not completeskill scan environmentno
    text
    security.exposure.open_channels_with_exec
    warn/criticalShared/public rooms can reach exec-enabled agents
    text
    channels.*.dmPolicy
    ,
    text
    channels.*.groupPolicy
    ,
    text
    tools.exec.*
    ,
    text
    agents.list[].tools.exec.*
    no
    text
    security.exposure.open_groups_with_elevated
    criticalOpen groups + elevated tools create high-impact prompt-injection paths
    text
    channels.*.groupPolicy
    ,
    text
    tools.elevated.*
    no
    text
    security.exposure.open_groups_with_runtime_or_fs
    critical/warnOpen groups can reach command/file tools without sandbox/workspace guards
    text
    channels.*.groupPolicy
    ,
    text
    tools.profile/deny
    ,
    text
    tools.fs.workspaceOnly
    ,
    text
    agents.*.sandbox.mode
    no
    text
    security.trust_model.multi_user_heuristic
    warnConfig looks multi-user while gateway trust model is personal-assistantsplit trust boundaries, or shared-user hardening (
    text
    sandbox.mode
    , tool deny/workspace scoping`)
    no
    text
    tools.profile_minimal_overridden
    warnAgent overrides bypass global minimal profile
    text
    agents.list[].tools.profile
    no
    text
    plugins.tools_reachable_permissive_policy
    warnExtension tools reachable in permissive contexts
    text
    tools.profile
    + tool allow/deny
    no
    text
    models.legacy
    warnLegacy model families are still configuredmodel selectionno
    text
    models.weak_tier
    warnConfigured models are below current recommended tiersmodel selectionno
    text
    models.small_params
    critical/infoSmall models + unsafe tool surfaces raise injection riskmodel choice + sandbox/tool policyno
    text
    summary.attack_surface
    infoRoll-up summary of auth, channel, tool, and exposure posturemultiple keys (see finding detail)no

    Related

    • Security
    • Configuration
    • Trusted proxy auth

    © 2024 TaskFlow Mirror

    Powered by TaskFlow Sync Engine