The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill acts on user-provided code and feature descriptions to generate test cases, creating a potential surface for indirect prompt injection. 1. Ingestion points: User-supplied source code and project specifications are analyzed during the 'Define scope' and 'Write tests' workflows. 2. Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the user-provided code. 3. Capability inventory: The skill does not contain instructions to execute shell commands, write to the file system, or perform network operations. 4. Sanitization: No sanitization or input validation logic is present in the skill instructions.

test-master