accessibility-testing

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install and configure external dependencies, specifically the pa11y/pa11y CLI tool and the axe-core runner, as development requirements.
  • [COMMAND_EXECUTION]: The instructions require the agent to run CLI tools (pa11y) and browser automation frameworks (Playwright) to perform accessibility checks against development builds.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests and processes external project data (source code and builds) that could contain malicious instructions designed to bypass assessment rules or manipulate report outputs.
  • Ingestion points: Development builds, individual features, and components isolated from the rest of the page (SKILL.md).
  • Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore embedded content in the processed projects.
  • Capability inventory: Subprocess execution (CLI tools), browser automation (Playwright), and file system modification (generating deliverables and regulatory information pages).
  • Sanitization: No sanitization or validation of the ingested data is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:40 PM
Security Audit — agent-trust-hub — accessibility-testing