Caveat verdict

code-generator

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

Generates code snippets locally; no network or credential‑related operations are performed.

⚠ 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.

48
security
100
transparency
90
maintenance

Findings (4)

Pattern match high

Pipe to python — executes piped content as Python code

scripts/script.sh · prose · downgraded · |python

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/script.sh · prose · downgraded · |sh

Pattern match medium

Dynamic import() — loads module at runtime

scripts/script.sh · prose · downgraded · import ( "

Pattern match low

Python os.environ.get — reads environment variable

scripts/codegen.sh · prose · downgraded · os.environ.get(

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