regression-tester
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses local command-line tools for their intended purpose in a developer workflow. No evidence of unauthorized data access, exfiltration, or persistence was found.
- [COMMAND_EXECUTION]: The skill utilizes git and various test runners (npm, pytest, go test, jest) to perform its core functions. These are standard operations for a regression testing tool.
- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill ingests and analyzes untrusted source code and diff data. 1. Ingestion points: git diff output and source code files analyzed in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local git and test commands. 4. Sanitization: No explicit sanitization or filtering of code content is performed. This surface is consistent with the skill's primary purpose and is considered a low-risk factor.
Audit Metadata