The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill workflow involves executing npx @axe-core/cli and npx lighthouse to perform scans. These are official tools provided by well-known technology organizations (Google and Deque Systems) and are used here according to their intended design.
[COMMAND_EXECUTION]: The skill includes instructions for the agent to run shell commands for auditing purposes. These commands are specific to the use of reputable accessibility tools and are directed at local or user-provided URLs.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data from external websites during audits.
Ingestion points: Content of web pages and user interfaces scanned via npx tools (referenced in SKILL.md).
Boundary markers: The instructions do not specify delimiters for tool output, though the tools used typically provide structured data (JSON/text reports).
Capability inventory: Command execution via npx and file system access for generating reports (detailed in SKILL.md).
Sanitization: No specific sanitization of the audited page content or tool output is described in the prompt instructions.

testing-accessibility-auditor