prd-writer
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected. The skill consists of instructional markdown for requirement engineering.
- [PROMPT_INJECTION]: The skill facilitates reading content from external issue trackers, which serves as a potential surface for indirect prompt injection if the source issues contain malicious instructions. This is an inherent property of the tool's intended workflow rather than a malicious instruction.
- Ingestion points: External tracker issue bodies (SKILL.md).
- Boundary markers: None explicitly defined for input; output follows a structured markdown template.
- Capability inventory: Limited to interacting with project tracker APIs for reading and writing PRDs.
- Sanitization: Relies on the agent's interpretation of the provided markdown structure.
Audit Metadata