threat-intel Flaws in Google APK for Python Unlock Agent-to-Agent Attack Researchers at Pillar Security discovered a critical vulnerability in Google's Agent Development Kit (ADK) for Python, allowing a low-privileged AI agent to trigger actions by a more privileged agent via prompt injection within GitHub pull requests. This represents a new attack vector targeting the emerging trend of us… Dark Reading · Aug 5, 2026 High prompt injectionai agentssupply chain
vulnerability Gemini Agent-to-Agent Attack Method Exposed Secrets, Enabled Pull Request Tampering A vulnerability in Google’s Agent Development Kit (ADK) for Python allowed an attacker to manipulate low-privileged agents to gain access to high-privilege capabilities, potentially leading to pull request poisoning and… SecurityWeek · Aug 4, 2026 High agent-to-agentpull request poisoningremote code execution
