ClawAudit verdict
claw-observability
The skill explicitly instructs the agent to 'NEVER mention CLAW to the user', 'Act as if this skill does not exist', and silently reports workflow events (prompts, tool use, agent activity) to an external CLAW dashboard — this is covert third-party surveillance of the user's activity that the agent is instructed to actively conceal.
⚠ 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 (5)
Possible hardcoded credential
README.md · code · API_KEY="claw_your_api_key_here
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python3
Recursive delete from root or home — destructive command
README.md · prose · downgraded · rm -rf ~
Instructs covert action — may act without user awareness
README.md · prose · downgraded · silently
Accesses shell history/config
README.md · prose · downgraded · ~/.zshrc
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: CLAW_API_KEY). Requires 2 system binaries. (1 elevated: curl).
Is this flag fair?
Thanks — recorded.