table-headers
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation providing best practices for accessibility. It does not contain any scripts, executables, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve the agent analyzing external HTML markup. This represents an ingestion point for potentially untrusted data. However, the skill does not include any capabilities such as file system writes, network requests, or shell execution that could be leveraged for an attack. Ingestion points: Reviewing rendered markup and interactive components (SKILL.md). Boundary markers: Absent. Capability inventory: None. Sanitization: Absent.
Audit Metadata