acceptance-tests

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess.run to execute git commands and project test suites via included Python scripts (brief.py, redgreen.py). These scripts implement robust safety measures, such as using list-based arguments for subprocess calls and a strict blacklist of shell metacharacters (SHELL_RE) to prevent command injection in user-defined test commands. Shell execution is explicitly disabled by default in the skill's instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data from .workflow/brief.md. Potential risks of malicious instructions being embedded in these files are mitigated by guidelines in pipeline.md, which instruct the agent to treat such content as data rather than instructions. Furthermore, the test execution path is protected by script-level validation and sanitization within the provided utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:22 AM