risk-register

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns detected. The skill provides templates and examples for risk assessment documentation.
  • [Indirect Prompt Injection] (SAFE): 1. Ingestion points: Agent uses Read, Grep, and Glob to read project files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Read, Grep, Glob (SKILL.md). 4. Sanitization: Absent. The risk is considered SAFE because the tools are restricted to reading files for documentation purposes and lack write, network, or execution capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:40 PM