zj-to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the conversation history and repository content to generate its output.
- Ingestion points: The agent reads the current conversation context and repository files as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters to separate untrusted context from instructions.
- Capability inventory: The agent is instructed to explore the repository and publish specifications to a project issue tracker.
- Sanitization: No explicit sanitization or filtering of the synthesized content is described before publication.
Audit Metadata