The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the agent to download and run the @axe-core/cli and lighthouse packages using npx to perform baseline accessibility scans. These are well-known tools from established organizations.- [COMMAND_EXECUTION]: The skill makes use of bash for executing audit commands and git for reviewing code changes and managing commits within the development environment.- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves processing untrusted data, which creates a standard vulnerability surface for indirect instructions.
Ingestion points: The agent reads project source code files and captures output from a local web server (e.g., http://localhost:8000) for its accessibility audit.
Boundary markers: The instructions lack explicit delimiters or specific warnings to the agent to ignore instructions that might be embedded within the content it analyzes.
Capability inventory: The skill has access to shell execution via bash, file system read/write operations, and git version control tools.
Sanitization: There is no evidence of content sanitization or validation performed on the external data before it is ingested by the agent for analysis.

a11y-auditor