focus-management
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation resource providing best practices for web accessibility. It includes React code examples for managing focus in modals, single-page applications, and form submissions. The content is educational and does not contain any executable scripts or network-active commands.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data in the form of rendered HTML markup and interactive components. An analysis of the attack surface reveals:
- Ingestion points: The skill instructs the agent to review rendered markup and interactive states provided by the user or project context (SKILL.md).
- Boundary markers: None specified.
- Capability inventory: The skill does not utilize any high-privilege tools, such as file system write operations, network requests, or shell command execution.
- Sanitization: No explicit sanitization or input validation is mentioned. Despite the lack of boundary markers, the absence of exploitable capabilities makes the risk associated with processing potentially malicious HTML minimal.
Audit Metadata