write-tests
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands through the quality_gates.py script to interact with the Git repository. These calls use subprocess.run with argument lists, which is a secure practice that prevents shell injection. The skill also instructs the agent to run the project's own test suite to verify new tests.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as project plans, code, and test reports. While this presents a potential surface for indirect prompt injection if those files contain malicious instructions, the skill's logic is constrained to test generation and validation, and it includes its own hygiene checks to detect suspicious code patterns. Evidence chain: ingestion points include plan files (Step 1) and test reports (suite command); boundary markers are absent; capabilities include subprocess execution (git and test runners); sanitization is present in the form of parameterized subprocess calls.
- [SAFE]: The provided Python script quality_gates.py relies solely on the Python standard library, minimizing external dependency risks. It also implements proactive security checks, such as identifying potential secret leaks and ensuring constant-time comparisons for sensitive data.
Audit Metadata