interview-me

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references design patterns adapted from a public GitHub repository (mattpocock/skills). This is a documented attribution for the methodology and does not involve automated remote code execution or untrusted downloads.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests repository content such as code, tests, and glossaries to provide context for user interviews, which presents a surface for indirect prompt injection.
  • Ingestion points: The agent reads existing repository files to inform the interview frontier (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing repository data.
  • Capability inventory: The skill is limited to writing markdown files to local paths such as .ai-workflow/work/ and docs/adr/ (SKILL.md, references/adr-template.md).
  • Sanitization: There is no mention of sanitizing or validating the content extracted from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:27 AM
Security Audit — agent-trust-hub — interview-me