The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external codebase data. Ingestion points: Repository files and conversation history referenced in SKILL.md. Boundary markers: None defined to isolate external data from the PRD template instructions. Capability inventory: Repository exploration tools and issue tracker publication. Sanitization: No sanitization or escaping mechanisms are described for the external content.
[SAFE]: The skill includes a human-in-the-loop validation step ('Check with the user') which reduces the risk of automated malicious actions. The external references are for attribution purposes and do not involve untrusted code execution.

to-prd