hermes-a2a-setup
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: 0.85). The required runtime path is the A2A plugin’s
pre_llm_callhook that “injects message into current session” from a remote agent’s A2A JSON-RPC payload (outsider-authored free text), which the LLM then consumes as prompt context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata