The Agent Skills Directory

[SAFE]: The skill is strictly focused on static code analysis of local SwiftUI source files. It explicitly instructs the agent to audit source code only and not to execute the application, which prevents risks associated with untrusted code execution.
[SAFE]: All searching and indexing are performed using local command-line tools like ripgrep (rg). No network activity, external API calls, or remote data exfiltration patterns were detected.
[SAFE]: There is no evidence of obfuscation, hidden instructions, or attempts to bypass AI safety guidelines. The instructions are transparent and aligned with the stated purpose of accessibility auditing.
[SAFE]: The skill does not access sensitive system paths (such as .ssh or .aws directories) or contain hardcoded credentials. It utilizes standard SwiftUI modifiers and patterns for its analysis.
[SAFE]: No persistence mechanisms, privilege escalation attempts, or dynamic context injections were found within the skill instructions or reference materials.

swiftui-wcag-accessibility-auditor