homarr-custom-widget
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as a code-generation assistant, authoring JSX widgets based on user-supplied requests and external context. This creates a surface for indirect prompt injection if the input contains instructions designed to manipulate the agent's behavior during the authoring process.
- Ingestion points: User-provided widget specifications and release context (SKILL.md).
- Boundary markers: The instructions do not specify the use of strict data delimiters or instructions to ignore embedded commands when processing these inputs.
- Capability inventory: The skill can execute the generated code via
customWidget_previewCreateand persist definitions usingcustomWidget_createFromPreview. - Sanitization: Significant protections are in place via a sandboxed JSX runtime (references/security.md) that prohibits dangerous operations such as imports,
eval, and direct browser network requests.
Audit Metadata