Caveat verdict

kernelgen-flagos

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

Unified dispatch skill for GPU kernel generation using documented sub-skills and MCP tooling; no credential access or unusual behavior beyond the stated GPU development 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.

30
security
70
transparency
70
maintenance

Findings (4)

Pattern match high

subprocess execution — runs system commands from Python

kernelgen-generate-for-flaggems.md · code · subprocess.run(

Pattern match high

Pipe to python — executes piped content as Python code

kernelgen-optimize-for-flaggems.md · prose · downgraded · | Python

Pattern match high

Writes to SKILL.md — self-modifying skill

README.md · prose · downgraded · SKILL.md dispatches here to verify that the kernelgen-mcp MCP service is configu

Pattern match medium

importlib.import_module — dynamic module loading

kernelgen-generate-for-vllm.md · code · importlib.import_module(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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