The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code files (HTML, JSX, Vue, Svelte, Astro) which represents a surface for indirect prompt injection if those files contain adversarial instructions.
Ingestion points: The scripts/scan-a11y.py script reads local files from user-defined paths specified in the CLI arguments.
Boundary markers: The script output is structured (TSV or JSON), but no specific boundary markers or instructions are provided to the LLM to ignore potentially malicious instructions embedded within the data being analyzed.
Capability inventory: The skill has access to Read, Write, and Bash tools, which it uses to execute the linter script and handle file operations.
Sanitization: The Python script performs basic comment stripping using regular expressions but does not sanitize for instructions that might target the agent's logic.

a11y-ops