ClawAudit verdict

virtual-forum

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill explicitly documents that it reads local SKILL.md files and transmits their full contents to an external Claude API endpoint, which could inadvertently exfiltrate sensitive information embedded in other skills; the skill itself flags this as a security warning, confirming the behavior is real.

⚠ 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.

60
security
90
transparency
100
maintenance

Findings (2)

Pattern match high

Uses exec() — may execute shell commands

README.md · code · exec(

Pattern match high

Pipe to bash — executes piped content as shell commands

README.md · prose · downgraded · | bash

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

No declared permissions — minimal attack surface.

dynamic_eval

Is this flag fair?

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