to-prd
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository and conversation context to generate documents.
- Ingestion points: Repository files explored during the 'understand the current state of the codebase' step and the ongoing conversation context.
- Boundary markers: None; the instructions do not specify delimiters or markers to separate untrusted repo content from the agent's instructions.
- Capability inventory: The skill performs file system read operations to explore the repo and network write operations to publish content to an issue tracker.
- Sanitization: None; the skill is instructed to synthesize what it already knows directly into a template without explicit validation or escaping of the input data.
Audit Metadata