b24jssdk-vibecode

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The only runtime path shown is an app-initiated call to VibeCode’s AI endpoint using user/derived content (e.g., messages: [{ role: 'user', content: ... }]), but there is no workflow step that ingests outsider-authored free text from an inbox/feed/ticket/queue or other submission surface by itself.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill contains a runtime fetch to the VibeCode AI endpoint (https://vibecode.bitrix24.tech/v1/ai/chat/completions) which returns AI-generated content that is injected into and used by the agent's workflow, creating a runtime external dependency that can directly influence prompts/output.