Caveat verdict

rocm_vllm_deployment

rocm-vllm-deployment

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

Production vLLM deployment automation on AMD ROCm GPUs using Docker Compose; the skill explicitly states it never writes HF_TOKEN to compose files and all operations are local infrastructure management matching the stated deployment 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.

25
security
70
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.bash_profile

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Why the tier is capped

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

credential_access

Is this flag fair?

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