agent-protocol

Warn

Audited by Snyk on Apr 3, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests untrusted agent metadata and responses from arbitrary A2A endpoints (see A2AClient.discover() which GETs "{base_url}/.well-known/agent.json" and ProtocolBridge.mcp_tool_to_a2a_task which sends tasks to external agent URLs and consumes their artifact parts), so third‑party agent content can directly influence tool selection and subsequent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 11:12 AM
Issues
1