web-accessibility

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or sensitive data access were found in the skill definition. The content is purely instructional and focused on WCAG standards.
  • [NO_CODE] (SAFE): The skill does not contain any executable scripts (Python, Node.js, Shell) or configuration files that define external dependencies. It relies entirely on the base LLM's reasoning capabilities.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process web content (HTML/CSS) for audits. While this is a surface for indirect prompt injection, the skill itself lacks any dangerous capabilities (like file writing, command execution, or network access) that could be abused.
  • Ingestion points: User-provided HTML snippets or website URLs provided during interaction.
  • Boundary markers: Absent from the provided prompt templates.
  • Capability inventory: No technical capabilities or tools are defined within this skill.
  • Sanitization: Not applicable as no code is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:11 PM