testing
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill processes external web content and local source files, which represents an inherent surface for indirect prompt injection. However, this behavior is essential for the skill's primary purpose.
- Ingestion points: Web pages via Chrome DevTools, local source files via Glob, Grep, and Read tools.
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: Bash, Write, and Edit tools are available to the agent for managing tests.
- Sanitization: No explicit sanitization of external content is defined.
- Command Execution (SAFE): The skill provides standard Maven commands and shell utilities necessary for locating and running tests. No arbitrary or high-risk command execution patterns were detected.
Audit Metadata