adk-agent-extension

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill config (adk_agent_list.json) and SKILL.md show the extension connects to user-configured ADK server URLs (e.g., "https://my-adk-server.example.com") and exposes tools like list_adks, create_session, and send_message_to_agent that ingest and act on responses from those external ADK servers, so arbitrary third‑party server content could influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 07:40 AM