to-spec
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it synthesizes untrusted data from the current conversation context to generate content that is published to an external project issue tracker.
- Ingestion points: The skill consumes 'current conversation context' as defined in SKILL.md.
- Boundary markers: There are no boundary markers or explicit instructions to treat user conversation as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill utilizes the agent's ability to read the codebase ('Explore the repo') and write to external systems ('publish it to the project issue tracker').
- Sanitization: The instructions lack any requirement for sanitizing, validating, or escaping the processed conversation context before inclusion in the final specification.
Audit Metadata