test-verification
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill serves its stated purpose as a testing and verification helper.
- [COMMAND_EXECUTION]: The skill instructions involve running tests and executing commands for bug reproduction and verification. These are standard operations for a development-focused agent and are restricted to the local development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from the local project environment, such as existing test files and project memory.
- Ingestion points: Reads project testing memory and existing test patterns (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: The agent is instructed to run unit, integration, API, and browser tests, which involves executing shell commands and scripts.
- Sanitization: Absent. While the surface exists, this is an inherent part of the skill's functionality as a testing assistant.
Audit Metadata