optimization-catalog
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a static organizational index for GPU kernel optimization knowledge. No malicious patterns, command executions, or data exfiltration attempts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a structure for reading local documentation files from
docs/knowledge/optimizations/anddocs/knowledge/anti-patterns/. This represents a data ingestion surface; however, as the targets are local project-specific markdown files rather than untrusted external sources, this pattern is evaluated as safe.
Audit Metadata