The Agent Skills Directory

[SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were detected. The skill provides legitimate guidance for standard software development and testing workflows.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading and executing user-provided code and tests, which is a standard developer tool capability but represents an inherent injection surface. 1. Ingestion points: The agent is instructed to read and judge user-provided test and code modules. 2. Boundary markers: No specific delimiters or safety instructions for handling embedded code instructions are provided. 3. Capability inventory: The skill requires the agent to run tests, which involves code execution within the agent's environment. 4. Sanitization: No input sanitization or validation steps are defined.

test-hygiene