interview-me
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues detected. The skill is composed of Markdown instructions and reference examples designed to guide the agent through a collaborative user interview process.
- [NO_CODE]: The skill consists entirely of documentation and instructions. It does not include scripts, binaries, or active code components.
- [PROMPT_INJECTION]: The skill is designed to ingest data from external sources like Linear/Jira tickets and codebases. This creates a surface for indirect prompt injection if those sources contain malicious instructions. However, the risk is mitigated as the skill uses this data purely for contextual synthesis during an interview, which is a standard and low-risk use case.
- Ingestion points: External tickets, design documents, and codebase files (SKILL.md).
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: The skill utilizes interaction tools (AskUserQuestion); it does not perform file writes or network exfiltration.
- Sanitization: Not specified.
Audit Metadata