ic-inbox
Warn
Audited by Snyk on Jul 19, 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 workflow reads outsider-authored inbox content (e.g.,
envelopes[].intent.payload.messagefrom other members’ agents) via the runtime A2A/MCP calls (ic_agent_inbox_get_thread/tasks/send), which becomes readable free text in the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata