The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and run the @axe-core/cli package. This is a widely recognized and industry-standard tool for accessibility testing.
[COMMAND_EXECUTION]: The skill executes shell commands to perform its audit functions:
Runs grep to scan JSX, TSX, and HTML files for static accessibility violations.
Runs npx @axe-core/cli@4 http://localhost:3000 to perform dynamic analysis against a local development server.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes untrusted project source code.
Ingestion points: Processes package.json and project files with extensions like .html, .jsx, .tsx, and .vue as specified in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded content are defined.
Capability inventory: The agent has the capability to execute shell commands (grep, npx) and read local files.
Sanitization: No explicit sanitization or filtering of the processed file content is mentioned.

a11y-audit