to-spec
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content and conversation history.
- Ingestion points: Codebase and conversation context are ingested to generate specifications.
- Boundary markers: Absent; no instructions are provided to distinguish codebase content from instructions.
- Capability inventory: The agent can publish content to an external issue tracker.
- Sanitization: Absent; no escaping or validation is performed on the codebase data before it is published.
Audit Metadata