web-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses standard, well-known developer tools (
eslint,lighthouse) vianpxto perform its primary function. These tools are fetched from a well-known registry. - [SAFE]: Data processing is performed locally, and audit results are stored within the project's local hidden directory structure (
.claude/skills/). - [INDIRECT_PROMPT_INJECTION]: The skill processes local source code files for accessibility issues. While this represents an ingestion point for untrusted data, the skill only performs static analysis and generates audit reports, presenting no significant capability for automated exploitation.
- [SAFE]: No patterns of obfuscation, malicious code execution, or data exfiltration were identified in the instructions or helper scripts.
Audit Metadata