ClawAudit verdict
shark
The skill provides non-blocking execution for AI coding agents, with legitimate use of process execution capabilities.
⚠ 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)
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Uses spawn() — can execute external programs
promo-thread.md · code · spawn(
References agent configuration files
README.md · prose · downgraded · CLAUDE.md
Popular HTTP library — network access
shark-exec/SKILL.md · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.
process_exec Is this flag fair?
Thanks — recorded.