pm-prd-review

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a simple Bash script in its preamble to check for the existence of requirement documents in the docs/02-方案设计/ directory. This is a benign discovery operation using standard if [ -f ... ] and echo commands.- [DATA_EXPOSURE]: The skill interacts with local files in the docs/ directory. It reads existing requirement documents and writes a review report. All file operations are scoped to project documentation and require user confirmation or existing context, presenting no risk of sensitive data harvesting.- [INDIRECT_PROMPT_INJECTION]: The skill reads external data (PRD/BRD files) for review. While this is an ingestion surface for untrusted data, the skill includes a structured verification checklist for its analysis, which mitigates the risk of instructions embedded in those documents influencing the agent's logic. As the primary purpose is document review, this is a standard and low-risk design pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 01:16 PM