ClawAudit verdict
skill-release-audit
This is a static pre-publish quality checker for AI agent skills that performs six analysis modules (syntax, completeness, edge cases, data safety, dependency declaration, documentation) entirely locally without network access or file modification — it is a pure read-only auditing 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.
Permission integrity
package_install
Findings (9)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
apt-get install — installs system packages
references/dep-patterns.md · code · apt-get install
Pipe to sh — executes piped content as shell commands
scripts/check_logic.py · prose · downgraded · |sh
Instructs covert action — may act without user awareness
scripts/healthcheck.py · prose · downgraded · silently
References child_process — can spawn system processes
scripts/check_deps.py · prose · downgraded · child_process
subprocess execution — runs system commands from Python
scripts/check_deps.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
SKILL.md · prose · downgraded · os.getenv(
Python os.environ.get — reads environment variable
scripts/_common.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/check_edges.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/D). 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.
package_install Is this flag fair?
Thanks — recorded.