wcag-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown documentation. It does not contain any Python scripts, Node.js code, shell scripts, or other executable files. It functions as a structured template and set of instructions for an AI agent to follow manually.
- [PROMPT_INJECTION]: The skill instructs the AI agent to ingest and analyze external data from user-supplied 'urls_or_screenshots'. This creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent is prompted to review external web content and screenshots as part of the Preparation and Testing phases (Step 1-3) in the SKILL.md file.
- Boundary markers: The skill lacks explicit instructions or markers to distinguish between the auditor's instructions and potentially adversarial content found on audited websites (e.g., hidden text, malicious alt-text, or script-injected content).
- Capability inventory: While the skill itself contains no code, it assumes the agent has access to web browsing capabilities and external automated testing tools (like axe DevTools or Lighthouse) to perform the audit.
- Sanitization: There are no protocols defined for the agent to sanitize, escape, or validate the integrity of the external content before processing it for the final report.
Audit Metadata