The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted source code files.
Ingestion points: The skill uses Glob and Read tools to ingest local source files (e.g., src/utils/parser.ts) to extract logic for test generation.
Boundary markers: The instructions lack delimiters or explicit warnings to the agent to disregard instructions that might be embedded within the source code being analyzed.
Capability inventory: The agent has the ability to write to the file system (Write, Edit) and execute shell commands via Bash(test:unit-*) and bundled scripts like test_runner.sh.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content read from source files before it is used to generate executable test code.
[COMMAND_EXECUTION]: The skill generates executable code and instructs the agent to run it locally.
Evidence: The instructions explicitly state to "Run the generated tests to verify they pass" and reference using npm test, pytest, or the bundled test_runner.sh.
Risk: If the agent is influenced by malicious content in a source file, it could generate and then execute malicious test code.

generating-unit-tests