ClawAudit verdict

baml-codegen

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill uses official BoundaryML repositories and supports multimodal inputs, but its capabilities could be misused if not properly secured.

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

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

40
security
90
transparency
70
maintenance

Findings (4)

Pattern match high

Pipe to python — executes piped content as Python code

references/languages-other.md · prose · downgraded · | Python

Pattern match high

Dynamic import() — loads module at runtime

references/languages-typescript.md · code · import('

Pattern match medium

Python os.environ.get — reads environment variable

references/BAML-REFERENCE-SOURCE.md · code · os.environ.get(

Pattern match medium

Accesses sensitive environment variables

references/BAML-REFERENCE-SOURCE.md · code · process.env.OPENAI_API_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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