autogen-multi-agent-workflow
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The workflow’s “Researcher” role uses an architecture-defined retrieval tool surface to fetch source material at runtime, and that retrieved public/outsider-authored text is then ingested into the agents’ LLM context for the Critic/Writer to ground and cite.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata