The Agent Skills Directory

[SAFE]: The skill's primary function is as a knowledge base and advisory tool for implementing accessibility standards (WCAG 2.1/2.2). It contains no instructions that attempt to bypass AI safety filters or override system constraints.
[SAFE]: All code snippets across the 10 reference files (React, SwiftUI, Jetpack Compose, etc.) are standard, best-practice implementations for accessible UI components. Examples include focus management for modals, ARIA live regions for announcements, and semantic HTML structures.
[SAFE]: There is no evidence of data exfiltration or unauthorized network operations. The skill does not access sensitive local files (such as SSH keys or environment variables) and does not contain hardcoded credentials.
[SAFE]: No obfuscation techniques (such as Base64, hex-encoding, or zero-width characters) were detected in the instructions or code examples. The skill metadata and documentation are consistent with its stated educational purpose.
[SAFE]: The skill provides an attack surface for Indirect Prompt Injection by auditing provided code; however, it lacks any dangerous capabilities (tools) or shell execution paths that could be exploited by malicious input.

accessibility-expert