The Agent Skills Directory

[SAFE]: No security issues detected. All analyzed patterns are consistent with the skill's stated accessibility auditing purpose.
[COMMAND_EXECUTION]: The skill utilizes standard auditing commands such as npx @axe-core/cli and npx lighthouse to scan for accessibility violations.
[EXTERNAL_DOWNLOADS]: Dependencies for auditing are sourced from the well-known npm registry, which is considered a safe and standard practice.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection given its function of auditing external web content.
Ingestion points: Analyzes content from web pages or local interfaces (e.g., http://localhost:8000).
Boundary markers: Not explicitly defined in the prompt instructions.
Capability inventory: Includes the ability to execute auditing commands and generate code remediation.
Sanitization: No explicit sanitization of audited content is described.

testing-accessibility-auditor