ClawAudit verdict

sglang-amd-bench

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

The sglang-amd-bench skill benchmarks sglang serving performance on AMD Instinct GPUs. While its intentions seem benign, the executionSinkDetected flag and specific rules about not modifying the environment could indicate potential risks if not carefully managed.

⚠ 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.

85
security
50
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Why the tier is capped

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

network_innetwork_out

Is this flag fair?

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