real-time
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required runtime workflow streams “steps/findings” into the frontend via Convex real-time subscriptions (
useQuery(getSteps/getFindings/getEdges/get)), and those DB fields are populated by the orchestrator from tool outputs that can include outsider-authored free text (e.g., scraped/public web content or other third-party messages), which then becomes LLM-readable prose in the agent context when the orchestrator incorporates it intoconversationHistory/reasoning for subsequent steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata