testing

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is primarily documentation-based, providing universal testing principles and technology-specific tool recommendations. All referenced external links point to official documentation for established testing frameworks and the author's own GitHub repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a file context that automatically ingests project test files (e.g., **/tests/**, *.test.*). While this is a standard operational requirement for a testing skill, it creates a theoretical surface where malicious instructions embedded in third-party test code could be read by the agent.
  • Ingestion points: SKILL.md includes multiple patterns to capture test-related files from the workspace.
  • Boundary markers: No specific delimiters or safety warnings are provided for the agent when processing these files.
  • Capability inventory: The skill itself does not define any executable capabilities; it only provides reference information.
  • Sanitization: No sanitization is performed on the ingested file content.
  • [COMMAND_EXECUTION]: SKILL.md includes command-line examples for running mutation testing tools such as Stryker, Infection, and Mutmut. These are standard industry tools, and the examples are provided for educational purposes within the skill's intended development scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 05:09 PM