Google Agent Development Kit flaw lets one AI agent steer another

Feeds.4Sysops •IT News • August 4, 2026

A vulnerability in Google’s Agent Development Kit for Python enabled a low-privilege AI agent to trigger a more powerful agent through poisoned pull requests. The real-world attack chain could expose GitHub credentials and tamper with dependencies in a repository downloaded more than 90 million times. Source

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Agent-to-Agent Exploitation Discovered in Google's ADK for Python Pillar Security researchers identified a vulnerability in Google's Agent Development Kit for Python (adk-python) that allows a low-privileged AI agent to trigger a high-privileged agent through prompt injection. This exploit could lead to the extraction of sensitive GitHub credentials, including a GITHUB_TOKEN, enabling unauthorized modifications to pull requests. The attack exploits workflows that allow public-facing agents to interact with more privileged automation, exposing a significant risk in CI/CD environments. Google has since mitigated the vulnerabilities but deemed the exploit non-rewardable due to its reliance on social engineering. This incident marks the first practical demonstration of agent-to-agent exploitation in a production environment, highlighting the need for updated threat models. The affected repository has over 90 million downloads, indicating a wide scope of potential impact. Security professionals are urged to reassess their threat models and consider the implications of AI agents in their workflows. 8 sources 69

Extracted Entities

Google Agent Development Kit flaw lets one AI agent steer another

The full story

Extracted Entities

Attack Types (1)

MITRE ATT&CK (1)

Tools (1)