what-is-this

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behaviors or patterns detected. The skill facilitates documentation and onboarding through local file analysis.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted content from external project files.
  • Ingestion points: Local project files and documentation.
  • Boundary markers: Absent.
  • Capability inventory: Reading and summarizing file contents.
  • Sanitization: No explicit instruction to ignore embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 08:37 AM
Security Audit — agent-trust-hub — what-is-this