wcag-audit-patterns
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted data from external websites during accessibility audits. \n
- Ingestion points: External web content is loaded into the agent context via Playwright's page.goto() method and via various CLI tools. \n
- Boundary markers: The skill does not define specific delimiters or provide instructions to ignore malicious commands that might be embedded in the audited HTML or metadata. \n
- Capability inventory: The skill can execute JavaScript in a browser context, run shell commands via npx, and perform network operations. \n
- Sanitization: There is no documentation or implementation of sanitization or filtering for the external content before it is processed by the agent. \n- [COMMAND_EXECUTION]: The instructions include examples for running accessibility CLI tools (axe-core, pa11y, lighthouse) using npx, which involves the shell execution of packages from the npm registry. \n- [EXTERNAL_DOWNLOADS]: The skill documentation describes dependencies on external libraries and CLI tools, specifically axe-core, pa11y, and lighthouse, which are fetched from public registries.
Audit Metadata