perf-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats were identified. The skill consists of plain-text instructions for data synthesis and formatting.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external performance data, profiling evidence, and logs. While ingesting untrusted data is a theoretical vulnerability surface, the skill lacks any capabilities to execute commands, write files, or perform network requests. Furthermore, it contains a constraint requiring the model to only cite evidence found in logs or code, which acts as a grounding mechanism.
Audit Metadata