The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx to run accessibility auditing tools such as @axe-core/cli and pa11y on specified URLs.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and run accessibility packages from the public npm registry at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external web pages or pull requests during audits. While this creates a potential surface for indirect prompt injection, the risk is mitigated by the specific focus on accessibility metadata and the use of specialized auditing tools.
Ingestion points: Target URLs provided for scanning or PR content for manual review.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: Execution of shell commands via npx (axe-core, pa11y).
Sanitization: Relies on the inherent parsing logic of the recommended auditing tools.

accessibility-audit