accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends industry-standard accessibility tools @axe-core/cli and Lighthouse for auditing.
- [INDIRECT_PROMPT_INJECTION]: The skill audits external web content, creating a surface for indirect prompt injection. Ingestion points include tools like lighthouse_audit and take_snapshot in SKILL.md. Boundary markers are present in the Anti-Patterns section, explicitly warning against trusting external output. The capability inventory is limited to standard audit tools and editor actions. Sanitization relies on adherence to the provided safety protocols.
- [COMMAND_EXECUTION]: Provides instructions for executing audit commands in a local shell environment, which is appropriate for the skill's development-focused task.
Audit Metadata