Caveat verdict

little-steve-agent-guard

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

Security guard skill wrapping agent command execution with risk assessment and audit logging; cross-skill read access is by design and disclosed, and the skill explicitly prohibits autonomous bypass of its own controls.

⚠ 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.

10
security
100
transparency
90
maintenance

Findings (4)

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script>

Pattern match high

Pipe to bash — executes piped content as shell commands

scripts/guard-exec.sh · prose · downgraded · |bash

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/guard-exec.sh · prose · downgraded · |sh

Pattern match high

Pipe to python — executes piped content as Python code

scripts/guard-exec.sh · prose · downgraded · |python

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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