The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script build-coverage-matrix.py located within the plugin root to process scan data. It uses variables derived from file paths and user-provided slugs to construct the command line. This is a standard operation for the skill's intended purpose of data processing.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from external files (scan-output.json and markdown reports) located in the workspace.
Ingestion points: Reads research/.metadata/scan-output.json and the markdown reports referenced by the output_file field in those JSON files.
Boundary markers: No specific delimiters or instructions to ignore embedded content are used when reading these files.
Capability inventory: The agent has access to Bash (for script execution), Write, Edit, Read, Glob, and Grep tools.
Sanitization: No explicit sanitization or validation of the file content is mentioned in the instructions, although the actual processing is offloaded to a Python script.

portfolio-consolidate