interview-me
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill content is limited to natural language instructions in Markdown format. There are no scripts, binaries, or automated shell commands included in the skill definition.- [SAFE]: No external dependencies, remote code patterns, or network operations were detected. The skill operates entirely within the context of a user conversation.- [SAFE]: No obfuscation, hidden instructions, or credential-harvesting patterns are present.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user input which constitutes a data ingestion surface. However, the agent's capabilities are restricted to conversational processing and optional file creation in a project documentation folder, posing no significant security risk.
- Ingestion points: User responses during the interview turns.
- Boundary markers: The skill requires a structured confirmation and restatement turn, acting as a manual check before finalizing intent.
- Capability inventory: Optional file write to
docs/intent/. - Sanitization: Relies on manual confirmation by the user rather than automated filtering.
Audit Metadata