unit-testing-test-generate

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The CoverageAnalyzer class utilizes subprocess.run to execute a test_command argument. This pattern is vulnerable to command injection if the command or its parameters are derived from untrusted input or manipulated project configuration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
  • Ingestion points: The skill reads local source files via open(file_path) and processes them using the ast module in the TestGenerator class.
  • Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between its system instructions and the untrusted code content being analyzed.
  • Capability inventory: The skill includes methods for system command execution (subprocess.run) and is designed to generate executable code templates for various languages.
  • Sanitization: No validation or sanitization of the content extracted from the source files is performed before it is used for test generation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:50 AM