build-agent-broker-project
Warn
Audited by Snyk on Aug 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Runtime text ingestion can include outsider-authored free text from A2A inputs (e.g.,
@request.payload.message.parts[0].textin the broker’s generator/reasoning prompts), because an external caller can send arbitrary message content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata