project-intake
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as project drafts, prototypes, and repository links provided by users.
- Ingestion points: User-provided inputs (descriptions, PRD drafts, figma links) in SKILL.md.
- Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard potential instructions embedded within the user-provided project data.
- Capability inventory: The skill has the capability to write to the file system (specifically
docs/00-intake.md). - Sanitization: There are no instructions for sanitizing or escaping the content from external inputs before writing it to the intake document.
Audit Metadata