to-prd
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content and conversation history to generate a PRD, which is then published to an external issue tracker.
- Ingestion points: The skill reads the current codebase and conversation context to synthesize the PRD (SKILL.md).
- Boundary markers: No delimiters are used to separate user data or repository content from the agent's instructions, nor are there warnings to ignore embedded commands.
- Capability inventory: The agent uses tools to read the local filesystem (repo exploration) and network-based tools to write to an external issue tracker.
- Sanitization: The skill does not implement validation or escaping of the content extracted from the repository or conversation history before publishing it.
Audit Metadata