The Agent Skills Directory

[SAFE]: No evidence of malicious behavior, credential harvesting, or unauthorized persistence mechanisms was found.
[EXTERNAL_DOWNLOADS]: The skill includes documentation references to well-known industry sources such as the W3C Web Accessibility Initiative, Mozilla Developer Network (MDN), and Google’s web.dev. These are reputable sources for technical guidelines.
[COMMAND_EXECUTION]: The skill leverages shell tools (Bash, Grep, Glob) for the legitimate purpose of scanning and auditing local project files for accessibility violations. Access is scoped to common file operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted web code from user projects, presenting a potential surface for indirect injection.
Ingestion points: Reads HTML, JavaScript, and CSS files provided by the user (SKILL.md).
Boundary markers: Absent; the skill does not use specific delimiters to wrap or neutralize instructions embedded within analyzed code.
Capability inventory: Has access to Bash, Read, Write, Grep, and Glob for file manipulation.
Sanitization: No sanitization or validation is applied to external code content prior to analysis.

web-accessibility