skills/danielmiessler/claude-code-plugins-plus/scanning-for-accessibility-issues/Gen Agent Trust Hub
scanning-for-accessibility-issues
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions and documentation for performing accessibility audits using a dedicated plugin and helper scripts. No malicious code, obfuscation, or unauthorized data access patterns were identified in the provided files. The stated purpose aligns with the behavior described.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external web content and UI components for accessibility compliance. This introduces an attack surface for indirect prompt injection, as the agent processes data that could be controlled by a third party.
- Ingestion points: Webpages and specific UI components provided by the user for auditing (described in SKILL.md).
- Boundary markers: No explicit boundary markers or delimiters for untrusted content are defined in the instructions.
- Capability inventory: The skill invokes the
a11y-scancommand and utilizes Python scripts for parsing guidelines and generating reports. - Sanitization: The documentation does not describe specific sanitization or filtering of the content being scanned.
Audit Metadata