nocobase-ai-knowledge-base-manager

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for this skill ingests user-provided free text via the skill input contract (e.g., action, target, identifier, knowledgeBasePrompt, and especially payload fields like query in nb api kb run-hit-test --query <text>), meaning an outsider can submit arbitrary content that the LLM consumes to perform KB/doc retrieval testing.