to-prd

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to transform existing dialogue and repository documentation into a structured PRD. It does not perform any sensitive operations outside of standard project management tasks.
  • [DATA_EXPOSURE_&_EXFILTRATION]: While the skill reads repository files such as ROADMAP.md and decision logs (docs/decisions/), this data is used exclusively to populate the PRD template. There are no patterns suggesting data is sent to unauthorized external domains.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use repository exploration tools to gather context. It does not execute arbitrary shell commands, privileged operations, or remote scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from repository files (ROADMAP.md, docs/decisions/). Although these are external ingestion points, the risk is negligible as the skill uses a fixed template to generate documentation rather than executing logic based on the content of those files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:01 AM
Security Audit — agent-trust-hub — to-prd