prd-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs standard development workflow automation. It facilitates the creation of project documentation by interviewing the user and checking local files.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface that processes untrusted content.
- Ingestion points: Local
README.md,specs/README.md, package manifest files, and direct user input during the interview process (SKILL.md). - Boundary markers: The skill utilizes a structured Markdown template (
templates/prd.md) to organize output, which provides logical separation between context and data fields. - Capability inventory: The skill is limited to reading local text files and writing new Markdown files to the
.prd/directory. - Sanitization: No explicit sanitization of the input data is described, but the risk is minimal as the output is static documentation.
Audit Metadata