to-prd
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests repository content and conversation history which could potentially contain malicious instructions embedded in data.
- Ingestion points: Repository files and conversation context (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill has the capability to write and publish content to the project issue tracker (SKILL.md).
- Sanitization: No sanitization of ingested data before publication is specified.
- [SAFE]: The skill's primary purpose is document generation and repository analysis. It uses standard templating and interaction patterns with no identified malicious vectors or unauthorized data access.
Audit Metadata