The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/scan_docs.py is designed to execute the ripgrep (rg) utility to facilitate fast documentation searches. The script implementation uses subprocess.run with a list of arguments and avoids the use of shell=True, which is a secure pattern that prevents command injection.
[SAFE]: The skill operates entirely on local application files (ecu.test installation directories) as configured by the user via environment variables or a .env file. There are no network operations, credential exposures, or obfuscated code segments detected in the provided files.
[PROMPT_INJECTION]: The skill reads and processes external data in the form of local HTML and RST documentation. While this creates a surface for indirect prompt injection, it is considered safe in this context as the data source is the local installation of a trusted software product.
Ingestion points: Documentation files read by scripts/scan_docs.py and scripts/search_api.py.
Boundary markers: None present in tool output.
Capability inventory: Local file reads and subprocess.run for rg searches.
Sanitization: Standard regex and string matching used for searching without content sanitization.

ecutest-api-skill