The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/coverage_map.py executes git via subprocess.run(). It passes arguments as a list and avoids shell=True, which is a secure method for executing external binaries.
[INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes source code files within a repository, creating a surface where malicious code could attempt to influence the agent. Ingestion points: The script scripts/coverage_map.py reads file contents via Path.read_text. Boundary markers: The skill does not define specific delimiters for processed code but mandates grounding findings in evidence. Capability inventory: Subprocess execution of git and file system access. Sanitization: Uses errors="replace" during file reading to handle malformed content.

test-gap-audit