The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions mandate generating and executing temporary Python scripts using uv run python or python3 to audit data. This is a standard pattern for data-intensive tasks where the agent must perform complex calculations on local datasets.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from project files like README.md, AGENTS.md, and .dta file metadata to inform its analysis.
Ingestion points: Processes README.md, AGENTS.md, CLAUDE.md, and .dta data/metadata.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill can execute Python code (python3) and write markdown files to the local file system.
Sanitization: No sanitization or validation of the ingested file content is performed prior to processing.

pipeline-audit