Caveat verdict

skillguard

skillguard-asi

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

A local security scanner analyzing skill ZIP files for OWASP ASI threats using Python stdlib with no network dependencies; scope is local-only static analysis.

⚠ 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 (9)

Pattern match high

Uses eval() — can execute arbitrary code

skillguard/detectors/code_execution.py · prose · downgraded · eval(

Pattern match high

Pipe to bash — executes piped content as shell commands

skillguard/detectors/network_whitelist.py · prose · downgraded · |bash

Pattern match high

Pipe to python — executes piped content as Python code

skillguard/detectors/network_whitelist.py · prose · downgraded · |python

Pattern match medium

Uses exec() — may execute shell commands

skillguard/detectors/code_execution.py · prose · downgraded · exec(

Pattern match medium

os.system/popen — direct OS command execution

skillguard/detectors/code_execution.py · prose · downgraded · os.system(

Pattern match medium

subprocess execution — runs system commands from Python

skillguard/detectors/code_execution.py · prose · downgraded · subprocess.run(

Pattern match medium

Accesses .ssh directory

skillguard/detectors/sensitive_file_access.py · prose · downgraded · .ssh/

Pattern match low

References tunneling service

skillguard/detectors/network_whitelist.py · prose · downgraded · ngrok

Pattern match low

Python os.getenv — reads environment variable

skillguard/detectors/secret_exposure.py · prose · downgraded · os.getenv(

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?

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