ClawAudit verdict
skill-lint
Quality and format audit tool for Claude Code Skills performing static analysis; no credential access or external network calls.
⚠ 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 (13)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
references/security-assessment-standards.md · prose · downgraded · curl | sh
Pipe-to-shell pattern (wget | sh)
references/security-assessment-standards.md · prose · downgraded · wget | bash
References sudo — requests elevated privileges
references/skill-dev-guide.md · code · sudo
Pipe to bash — executes piped content as shell commands
references/security-assessment-standards.md · prose · downgraded · | bash
Pipe to sh — executes piped content as shell commands
references/security-assessment-standards.md · prose · downgraded · | sh
apt-get install — installs system packages
references/skill-dev-guide.md · code · apt-get install
Recursive delete from root or home — destructive command
references/skill-dev-guide.md · prose · downgraded · rm -rf ~
Pipe to python — executes piped content as Python code
references/structure-standards.md · prose · downgraded · | Python
setuid — privilege escalation mechanism
references/security-assessment-standards.md · prose · downgraded · setuid
subprocess execution — runs system commands from Python
references/security-assessment-standards.md · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
references/skill-dev-guide.md · code · os.getenv(
Sets world-executable permissions
references/security-assessment-standards.md · prose · downgraded · chmod 777
Opens WebSocket connection
references/security-assessment-standards.md · prose · downgraded · WebSocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
Is this flag fair?
Thanks — recorded.