research-to-prd
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes the full content of untrusted research documents.
- Ingestion points: The skill reads files from
docs/research/or arbitrary paths provided by the user. - Boundary markers: The instructions do not define specific delimiters (like XML tags) or safety headers to prevent the agent from following instructions embedded within the research documents.
- Capability inventory: The skill has permissions to read project documentation (
CONTEXT.md,triage-labels.md), write to the file system (.scratch/, project root), and prompt the user for input (AskUserQuestion). - Sanitization: There is no evidence of sanitization or content filtering for the data extracted from research documents before it is used to generate the PRD.
Audit Metadata