ClawAudit verdict

perfguard

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

PerfGuard scans local codebases for performance anti-patterns using regex matching with explicit statement that no code is sent to external servers; the license key is for tier gating in a legitimate commercial static analysis tool.

⚠ 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.

15
security
60
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (6)

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · frontmatter · ~/.openclaw/openclaw.json

Pattern match high

Pipe to python — executes piped content as Python code

scripts/patterns.sh · prose · downgraded · |Python

Pattern match medium

Instructs covert action — may act without user awareness

scripts/analyzer.sh · prose · downgraded · silently

Pattern match medium

Python asyncio subprocess — async shell execution

scripts/patterns.sh · prose · downgraded · asyncio.create_subprocess_shell(

Pattern match low

Popular HTTP library — network access

scripts/license.sh · prose · downgraded · got

Pattern match low

Opens WebSocket connection

scripts/patterns.sh · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 4 system binaries. (1 elevated: git).

credential_access

Is this flag fair?

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