conditional-docs-setup

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): Instructional phrases like 'IMPORTANT' are used solely for operational guidance on context management and do not target safety filter bypass or rule overriding.
  • [Data Exposure] (SAFE): The skill interacts exclusively with documentation files (.md, README). No sensitive file paths, environment variables, or hardcoded credentials were found.
  • [Indirect Prompt Injection] (SAFE): The skill reads external project documentation. Evidence: (1) Ingestion points: .md and README files; (2) Boundary markers: None; (3) Capability inventory: Read/Write tools; (4) Sanitization: Standard markdown processing.
  • [Command Execution] (SAFE): Shell commands are restricted to 'find' for locating documentation, posing no risk of unauthorized system modification or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:17 PM