interview-me
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a process for requirement gathering and design alignment. It relies on standard codebase exploration and interactive questioning tools provided by the host environment.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it reads codebase content (protobufs, schemas, documentation) which is externally controlled. The risk is minimized as the data is used to formulate questions for the user, and the skill does not perform high-privilege actions based on this data.
- Ingestion points: Reads existing implementations, models, schemas, and endpoints from the local codebase during the 'Silent Codebase Exploration' step in SKILL.md.
- Boundary markers: None explicitly defined in the prompt interpolation logic to separate codebase content from instructions.
- Capability inventory: Limited to file reading and invoking interactive user-prompt tools such as
AskFollowupQuestionorask_question. - Sanitization: No specific sanitization or escaping mentioned for the content read from the codebase.
Audit Metadata