ClawAudit verdict
anthropic-usage
Queries the user's own Anthropic Admin API usage data using their own admin key stored in their own config; the key is sent only to Anthropic's official endpoint, which is the legitimate intended use.
⚠ 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 (4)
Possible hardcoded credential
scripts/usage.sh · prose · downgraded · token="$next_page
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
References sudo — requests elevated privileges
README.md · prose · downgraded · sudo
Popular HTTP library — network access
tests/run_tests.sh · prose · downgraded · got
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
Requires 1 environment variable. (1 sensitive: ANTHROPIC_ADMIN_API_KEY). Requires 2 system binaries. (1 elevated: curl).
credential_access Is this flag fair?
Thanks — recorded.