to-spec-yes
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from the conversation history and codebase context to generate output that is published to an external issue tracker.
- Ingestion points: Conversation context and codebase content are read to generate the spec (SKILL.md).
- Boundary markers: None identified in the prompt instructions to delineate untrusted input.
- Capability inventory: The skill explores the local repository (file read) and publishes content to the project issue tracker (network/tool write).
- Sanitization: No explicit sanitization or validation of the synthesized input is described before publication.
Audit Metadata