ClawAudit verdict
pager-triage
PagerDuty incident management skill that reads incidents and acknowledges/resolves only with explicit --confirm flag; behavior precisely matches its stated triage purpose.
⚠ 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
SKILL.md · code · API_KEY="u+your_key_here
Accesses sensitive system files
TESTING.md · code · /etc/passwd
Recursive delete from root or home — destructive command
TESTING.md · code · rm -rf /
Writes to SKILL.md — self-modifying skill
SPEC.md · prose · downgraded · SKILL.md setup guide MUST recommend creating a **read-only** API key for initial
Popular HTTP library — network access
OPERABILITY.md · 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
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.