The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill presents an indirect prompt injection surface because it processes untrusted source code and project configuration files to generate test output. \n- Ingestion points: Reads project source code and metadata files like package.json and requirements.txt. \n- Boundary markers: No explicit delimiters or instructions are provided to separate the ingested code from the tool's logic. \n- Capability inventory: The skill is granted 'Read', 'Write', and 'Edit' permissions, allowing it to modify the project filesystem. \n- Sanitization: No sanitization or validation of the analyzed source code is described.

test-generator