interview-framework
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its dialogue-based requirement gathering process. 1. Ingestion points: Direct user input via triggers such as 'interview me' or 'clarify the request', and persistent state in
.progress.md(SKILL.md). 2. Boundary markers: No explicit delimiters or 'ignore' instructions are provided to separate user-supplied content from the skill's operational logic. 3. Capability inventory: The skill has the ability to read and write to various local files including.progress.md,.planning/intake/*.md, and.v7/decisions/*.json(algorithm.md). 4. Sanitization: There is no defined process for validating, escaping, or filtering user input before it is summarized or written to disk. - [NO_CODE]: The skill consists entirely of instructional markdown and reference documentation. No executable scripts, binary files, or remote dependencies are included in the provided files.
Audit Metadata