b24jssdk-frame-ui
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes an interface for ingesting data from the external Bitrix24 portal environment (e.g., via placement options and CRM selectors). This creates a surface for indirect prompt injection if the ingested data contains instructions for the AI agent.
- Ingestion points: Data enters via
placement.optionsand variousdialogpickers for users and CRM entities as described inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill facilitates portal-side actions including CRM record selection, UI state changes, and setting persistence.
- Sanitization: The documentation recommends type narrowing for data consistency but does not specify sanitization for natural language injection.
Audit Metadata