The Agent Skills Directory

[COMMAND_EXECUTION]: The skill implements a processing pipeline using local Python scripts (diff_parser.py, annotation_extractor.py, and review_html_renderer.py) to transform markdown input into HTML artifacts. These scripts rely exclusively on the Python standard library for logic and do not invoke external shells or perform unsafe subprocess executions.\n- [DATA_EXFILTRATION]: No network exfiltration or unauthorized data access patterns were detected. The scripts operate on local files provided via command-line arguments. The resulting HTML output references Google Fonts for typography, which is a well-known and trusted service.\n- [SAFE]: The skill demonstrates robust security practices by sanitizing all user-controllable data—such as PR titles, reviewer names, and annotation text—using html.escape() before embedding them into the HTML templates, effectively mitigating cross-site scripting (XSS) and injection risks.

md-review