iblai-api-agent-history

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow reads conversation history and summaries via the AI-analytics/reports API endpoints (e.g., .../chat-history/, .../summaries/general/, and export report download), which necessarily contains outsider-authored user chat text that is then ingested into the agent’s LLM context for summarization/reporting.