to-prd
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface, as it is instructed to synthesize a PRD from existing project context and publish it to an external issue tracker.
- Ingestion points: The skill explicitly instructs the agent to "Explore the repo" (SKILL.md) and use the "current conversation context" (SKILL.md).
- Boundary markers: No specific boundary markers or instructions are provided to the agent to ignore potentially malicious commands embedded in the codebase or user conversation during the synthesis process.
- Capability inventory: The skill reads repository files and writes to a remote issue tracker.
- Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the content before it is published to the project's issue tracker.
Audit Metadata