to-prd
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation history and local context files to generate a PRD that is then published to an external issue tracker.
- Ingestion points: The skill synthesizes the 'current conversation context' and reads project files from
.agent/context/ordocs/agents/into the agent's prompt context (SKILL.md). - Boundary markers: Absent. The PRD template does not use specific delimiters or instructions to prevent the agent from obeying instructions embedded within the conversation history.
- Capability inventory: The agent is instructed to explore the repository and publish the resulting PRD to an external issue tracker.
- Sanitization: Absent. The skill synthesizes information directly from the conversation into the PRD template without explicit filtering or sanitization steps.
Audit Metadata