ClawAudit verdict

clawdoc

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Agent session diagnostic tool with 14 pattern detectors for analyzing failures and cost spikes; uses standard shell tools for local analysis with no external data transmission.

⚠ 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.

33
security
100
transparency
90
maintenance

Findings (6)

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

Possible hardcoded credential

dev/generate-demo.sh · prose · downgraded · Secret: 'changeme

Pattern match medium

References agent memory files

docs/demo-output.md · code · MEMORY.md

Pattern match low

References agent configuration files

CLAUDE.md · prose · downgraded · CLAUDE.md

Pattern match low

Accesses sensitive environment variables

dev/generate-demo.sh · prose · downgraded · process.env.JWT_SECRET

Pattern match low

Popular HTTP library — network access

dev/run-stress-tests.sh · prose · downgraded · got

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 3 system binaries.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API