mb-from-prd
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Vulnerability to Indirect Prompt Injection.
- Ingestion points: The skill processes prd.md and user-provided text as the primary source for documentation generation.
- Boundary markers: The process lacks delimiters or specific instructions to isolate the PRD content, increasing the risk of the agent following instructions embedded within the PRD.
- Capability inventory: The agent can perform file system operations in the repository and execute secondary tools like /find-skills, /prd-to-tasks, and /autonomous.
- Sanitization: There is no mechanism described for sanitizing or validating the input data before it is used to influence the agent's behavior.
Audit Metadata