prd-writer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest data from untrusted external sources, creating a potential vector for indirect prompt injection.
- Ingestion points: According to the workflow in
SKILL.md, the agent is instructed to read "relevant product decisions, code, and existing behavior" as well as search through "issues and PRs for duplicates". - Boundary markers: The instructions lack requirements for using boundary markers or delimiters when processing this external content, which increases the risk of the agent following instructions embedded in the data.
- Capability inventory: The skill is authorized to create or modify the "requested canonical requirements document or authorized issue body", allowing for the potential propagation of malicious content to the repository tracker.
- Sanitization: No sanitization or validation steps are defined for the information retrieved from the repository before it is used to generate outputs.
Audit Metadata