accessibility

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely instructional and follows established web development best practices for accessibility.\n- [EXTERNAL_DOWNLOADS]: Recommends the use of lighthouse (by Google) and @axe-core/cli (by Deque). These are reputable, well-known tools in the web development ecosystem.\n- [COMMAND_EXECUTION]: Provides standard CLI commands for auditing websites. These commands are consistent with the skill's stated purpose of performing accessibility audits.\n- [PROMPT_INJECTION]: The skill provides instructions for auditing external websites, which inherently involves processing untrusted data. \n
  • Ingestion points: Content from external URLs provided by the user for auditing (referenced in SKILL.md). \n
  • Boundary markers: None specified in the provided guidelines to separate audited content from instructions. \n
  • Capability inventory: Execution of audit tools via shell (npx lighthouse, axe). \n
  • Sanitization: Not explicitly addressed in the instructional content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 05:01 AM