to-prd
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. Ingestion points: The skill ingests untrusted data from the current conversation context and the project codebase (SKILL.md). Boundary markers: Absent; there are no delimiters or instructions to ignore potential commands embedded in the ingested context. Capability inventory: The skill has the capability to read repository files and publish content to an external issue tracker (SKILL.md). Sanitization: Absent; no validation or escaping is performed on synthesized data before it is published.
Audit Metadata