The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external source code to generate test suites, which represents a potential surface for indirect prompt injection.
Ingestion points: Reads source code from the user-provided [path] as defined in references/generate-tests.md.
Boundary markers: Prompts for subagents do not include specific delimiters to isolate the code being analyzed from the instructions.
Capability inventory: The subagents utilize Read, Grep, and Glob tools for code analysis and the Write tool for creating generated test files.
Sanitization: The skill does not implement explicit sanitization or filtering of the source code content before processing.

test-generation