Agent-to-agent protocols

Google has fixed flaws in its APK for Python that allowed an agent-to-agent attack. The issues exploited a trust boundary between two AI agents with different privilege levels, triggering automation that could compromise the supply chain.

Pillar Security found an agent-to-agent attack method in Google's Agent Development Kit for Python (google/adk-python) that could expose secrets and enable pull request poisoning. A public-facing low-privileged agent could be manipulated into passing a prompt to a high-privileged maintainer agent, which exposed its tools via the MCP server and allowed remote command execution and extraction of its GitHub token. Google addressed the issue through hardening but did not consider it eligible for a bug bounty, and a later remote code execution flaw in the Antigravity-SDK-based agent's automation features was fixed in late July.