Vulnerability Disclosure

Vulnerability disclosure refers to the process of reporting security flaws in AI systems, software, or infrastructure to relevant parties such as vendors, regulators, or the public. In enterprise AI governance, responsible disclosure practices are critical for identifying and remediating risks before they can be exploited maliciously or cause harm. Organizations need clear policies defining timelines for disclosure, communication channels, and remediation procedures to maintain trust with stakeholders while protecting their systems and data from security threats.

1 item

ResearchGlobal2026-08-06

11 Framework Flaws Put Every Agentic App Built on LangChain, AutoGen, and Google ADK at Risk

Check Point Research disclosed 11 vulnerabilities across five major AI agent frameworks, including LangChain, CrewAI, AutoGen, Microsoft Agent Framework, and Google ADK. The flaws include classic bug classes such as insecure deserialization and path traversal embedded in the infrastructure enterprises use to build agentic AI applications. A critical flaw in Microsoft Agent Framework enabled remote code execution triggered through prompt injection, while a Google ADK issue allowed unauthenticated code execution and credential theft on default cloud deployments.

agentic AI AI security prompt injection vulnerability disclosure LangChain Microsoft Agent Framework Google ADK supply chain security