ClawAudit verdict
openclaw-ref
openclaw-reference
Platform reference skill pointing to structured documentation files about the OpenClaw codebase; purely instructional index with no executable code or credential access.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (7)
Accesses OpenClaw config/secrets directly
references/boot-provisioning.md · code · ~/.openclaw/openclaw.json
Attempts to modify skills or system prompts
references/plugin-system.md · prose · downgraded · replace system prompt
Instructs covert action — may act without user awareness
references/boot-provisioning.md · prose · downgraded · silently
Dynamic import() — loads module at runtime
references/boot-provisioning.md · prose · downgraded · import("
References webhook/callback URL
references/configuration.md · code · webhookUrl
Opens WebSocket connection
references/boot-provisioning.md · prose · downgraded · WebSocket
References agent memory files
references/configuration.md · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.