skills/sickn33/antigravity-awesome-skills/accessibility-compliance-accessibility-audit/Gen Agent Trust Hub
accessibility-compliance-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The implementation-playbook.md file contains scripts that utilize Puppeteer to automate browser tasks such as navigating to URLs and evaluating accessibility rules within the page context.
- [EXTERNAL_DOWNLOADS]: The CI/CD configuration in the playbook references official GitHub Actions for environment setup and artifact management, which are considered well-known and standard infrastructure components.
- [PROMPT_INJECTION]: The skill is designed to analyze external web pages, creating an attack surface for indirect prompt injection (Category 8). Ingestion points: Browser navigation to arbitrary URLs via Puppeteer in resources/implementation-playbook.md. Boundary markers: No explicit delimiters are used to separate audited content from instructions. Capability inventory: Includes browser automation and in-page script execution via page.evaluate. Sanitization: Content analysis is performed by the axe-core library without specific sanitization of input data before processing.
Audit Metadata