The Agent Skills Directory

[SAFE] (SAFE): No security risks identified across any of the analyzed files.
[Command Execution] (SAFE): The provided Python script scripts/api_validator.py performs static analysis of local files. It uses safe libraries (pathlib, re, json) and does not execute the files it scans.
[Data Exposure] (SAFE): The script only reads files matching specific API-related patterns (e.g., .ts, .py, .json, .yaml) and does not access sensitive system directories or credentials.
[Indirect Prompt Injection] (LOW): The validator script ingests untrusted data from the user's project files.
Ingestion points: api_validator.py reads text from files discovered in the project_path.
Boundary markers: None (outputs findings directly to stdout).
Capability inventory: File reading via Path.read_text(); no network or write capabilities.
Sanitization: None, but the output is used for informational purposes and does not influence agent control flow in a dangerous way.

api-patterns