a2a-protocol
Warn
Audited by Snyk on Jul 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: 0.70). High likelihood that outsider-authored free text is fed into an LLM via the provider adapters’ runtime ingestion of remote agent responses/stream messages (e.g.,
response.text()/ SSEdata: ...→TaskUpdate.message/TaskOutput.response), which can contain arbitrary user-injected content from an external agent endpoint.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata