experience-accessibility-validate
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for the legitimate purpose of performing accessibility reviews on web components. The instructions are focused and well-structured, referencing specific WCAG success criteria.
- [COMMAND_EXECUTION]: The skill utilizes a provided Python script (
scripts/contrast-ratio.py) to calculate contrast ratios. This script is a safe, localized utility that uses standard libraries (argparse,json,re) and does not perform network operations or access sensitive system files. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it processes user-provided LWC code (HTML, JS, and CSS).
- Ingestion points: LWC source files provided by the user for review.
- Boundary markers: Not explicitly defined in the instructions, but the agent is directed to produce a specific
a11y-review.mdoutput. - Capability inventory: The agent can run the local contrast script and generate markdown reports.
- Sanitization: The skill mitigates risks by instructing the agent to 'Focus Exclusively on Accessibility' and ignore violations not related to WCAG Success Criteria, which limits the likelihood of following instructions embedded in the analyzed code.
Audit Metadata