interview-me

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns were detected. The skill consists of instructional text for the AI agent to follow during a conversation.
  • [NO_CODE]: The skill does not contain any executable scripts, binaries, or system commands. Its functionality is entirely text-based.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve gathering and processing user answers to influence future agent behavior. While this establishes a data ingestion surface, there are no associated tools or execution capabilities defined in the skill that could be abused through this vector.
  • Ingestion points: User responses to questions posed via the AskUserQuestion tool (SKILL.md).
  • Boundary markers: None specified.
  • Capability inventory: None (no tools or shell access provided in the skill contents).
  • Sanitization: Not applicable as the skill does not include processing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 01:01 AM
Security Audit — agent-trust-hub — interview-me