to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted conversation history to generate technical specifications which are then published to an external issue tracker.
- Ingestion points: The skill ingests the "current conversation context" as the primary source for the specification (SKILL.md).
- Boundary markers: The specification template does not include explicit boundary markers or instructions to downstream agents to ignore embedded user instructions within the spec fields.
- Capability inventory: The skill possesses the capability to explore the repository codebase and publish content to a project's issue tracker. It specifically applies a
ready-for-agentlabel, which is intended to trigger further automated actions. - Sanitization: There are no instructions for sanitizing, validating, or filtering the conversation context before it is synthesized into the final published specification.
Audit Metadata