to-spec
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it synthesizes information from potentially untrusted external sources.
- Ingestion points: The skill instructions in
SKILL.mdrequire the agent to explore the repository (specifically domain glossaries and ADRs) and incorporate the current conversation context. - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore any hidden directions found within the files it analyzes.
- Capability inventory: The skill is designed to publish the synthesized specification to the project's issue tracker, providing an automated write capability for processed data.
- Sanitization: No sanitization, validation, or escaping of the ingested data is performed before it is published to the issue tracker.
Audit Metadata