kb-cognitive-accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the analysis of external, potentially attacker-controlled content, including page URLs, UI component source code, and plain text content blocks. This creates an attack surface for indirect prompt injection where malicious instructions could be embedded in the data being reviewed.
- Ingestion points: The skill processes external page URLs, UI component source files, and text blocks submitted for accessibility auditing.
- Boundary markers: The instructions do not define specific delimiters or use warnings to the agent to ignore instructions embedded within the data being analyzed.
- Capability inventory: No active capabilities such as network requests, file-system writes, or shell command execution were identified within the skill's instructions or example code.
- Sanitization: There are no instructions for sanitizing or escaping content before the agent evaluates it for compliance.
Audit Metadata