interview-me

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown-based instructions for agent conversational behavior.
  • [SAFE]: No external dependencies, package installations, or remote scripts are referenced or used.
  • [SAFE]: File system operations are limited to saving user-confirmed project intent documents within a specific local directory (docs/intent/).
  • [SAFE]: The skill processes user input but lacks dangerous capabilities like network access or arbitrary command execution. While it lacks boundary markers and sanitization for user responses (Ingestion points: SKILL.md Step 2/3), its capability inventory is restricted to user-gated file writes, making it safe from indirect prompt injection.
  • [SAFE]: No obfuscation, prompt injection attempts, or malicious patterns were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 08:30 AM
Security Audit — agent-trust-hub — interview-me