The Agent Skills Directory

[SAFE]: The skill's core logic is contained within a Python script (scripts/verify_accessibility.py) that performs read-only static analysis on user-provided HTML files using regular expressions. It does not use dangerous functions like eval(), exec(), or subprocess.
[SAFE]: All external resources mentioned in the documentation and references point to well-known, reputable organizations in the accessibility space, such as the W3C (w3.org), WebAIM (webaim.org), and NV Access (nvaccess.org).
[SAFE]: No network operations or data exfiltration patterns were identified. The script operates entirely on the local file system using the standard library (pathlib, re, json).
[SAFE]: The skill lacks persistence mechanisms, privilege escalation attempts, or prompt injection vectors. It adheres to the stated purpose of auditing web content for accessibility compliance.

accessibility-auditor