to-spec
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted conversation context and codebase information to generate content for an external issue tracker.
- Ingestion points: The skill ingests conversation context and codebase understanding as stated in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present for the ingested data.
- Capability inventory: The skill is instructed to publish data to a project issue tracker (SKILL.md), which involves external tool usage.
- Sanitization: There is no evidence of input validation or output sanitization before the synthesized content is published.
Audit Metadata