context-driven-testing
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No security issues were detected. The skill contains instructional content and high-level configuration examples for software quality engineering.
- Indirect Prompt Injection (INFO): The skill identifies a potential attack surface in Category 8, where project metadata (untrusted external data) is used to influence agent selection and testing strategy. However, this is inherent to the functional purpose of the skill (adaptive testing) and represents a low-risk internal reasoning influence rather than a high-privilege execution capability.
Audit Metadata