accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses well-known and trusted tools (Playwright, Axe-core) for accessibility auditing. All instructions and examples follow best practices for web development and automated testing.
- [DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were identified. The skill does not access sensitive files or perform suspicious network operations.
- [REMOTE_CODE_EXECUTION]: The skill involves local generation and execution of test scripts, which is standard for auditing tools. It does not download or execute remote code from untrusted sources.
- [PROMPT_INJECTION]: No direct prompt injection patterns were found. While the skill analyzes untrusted component code (Category 8 surface), the risk is mitigated by the specific technical focus of the instructions. Ingestion points: component code (SKILL.md). Boundary markers: absent. Capability inventory: Bash, Write, Edit, Read. Sanitization: absent.
Audit Metadata