pm-review-board
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for document analysis and review simulation. It does not perform any network operations, external downloads, or sensitive file access.
- [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found in the instructions or the checklist references.
- [SAFE]: The instructions for parallel sub-agents describe a cognitive workflow for the LLM rather than a system-level process execution.
- [SAFE]: While the skill ingests user-provided documents (PRDs/Prototypes) which represents an indirect prompt injection surface, the agent lacks any dangerous capabilities (e.g., shell access, file writing) to exploit, limiting potential impact to the integrity of the generated review output.
Audit Metadata