The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx to run command-line tools for web auditing. It uses Chrome with the --no-sandbox flag, which is standard for headless operations in restricted environments.
[EXTERNAL_DOWNLOADS]: Uses npx to fetch and execute reputable Node.js packages like @axe-core/cli and playwright from the npm registry.
[PROMPT_INJECTION]: The skill processes external web content, which is a surface for indirect prompt injection.
Ingestion points: Data enters via curl and scanning tools.
Boundary markers: None provided.
Capability inventory: Command execution and file writing.
Sanitization: No explicit sanitization of external data is defined.

web-scanning