user-background-interviewer
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's operations are confined to an interactive dialogue and writing to a local JSON file (
memory/user_profile.md). It does not use any tools for network communication or sensitive file access. - [NO_CODE]: The skill contains no executable scripts, binaries, or external dependencies, which significantly limits its security risk profile.
- [PROMPT_INJECTION]: The skill collects user data which represents an indirect injection surface, though the risk is low given the lack of dangerous capabilities.
- Ingestion points: User responses provided during the full, fast, or browse interview paths are captured and stored.
- Boundary markers: No explicit delimiters or boundary markers are used in the JSON output to isolate user-provided strings.
- Capability inventory: The skill does not possess capabilities for command execution, subprocess spawning, or network exfiltration.
- Sanitization: There is no evidence of input sanitization or escaping before the user data is written to the profile file.
Audit Metadata