brd
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a template and procedural guide for conducting interviews to build book requirements documents.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to read and process content from user-provided URLs and files. 1. Ingestion points:
SKILL.md(Research Sources Questions and template). 2. Boundary markers: Absent. 3. Capability inventory: File write (BRD.md) and database write capabilities defined inSKILL.md. 4. Sanitization: Absent.
Audit Metadata