Vulnerability  ·  2026-08-10

Check Point Research discloses 12 CVEs (21 flaws) across LangChain, CrewAI, Microsoft Agent Framework, and Google ADK agent frameworks

VulnerabilityHigh impactGlobal
At Black Hat USA 2026, Check Point researchers Shahar Tal and Yarden Porat presented 'No Tools Required: Post-Injection Exploitation Across AI Agent Frameworks,' disclosing 21 findings including 12 CVEs across LangChain, CrewAI, Microsoft Agent Framework, and Google ADK. The flaws include insecure deserialization (the 'LangGrinch' bug, CVE-2025-68664, CVSS 9.3), SSRF, and sandbox escapes. In several cases, no dangerous function is called directly by the attacker — a poisoned document lands in the agent's memory/RAG pipeline and the framework's own save/reload (serialization) behavior fires the payload automatically, exposing stored API keys, cloud credentials, and enabling RCE.
These are core orchestration runtimes underlying a large share of production LLM agent deployments. An attacker only needs to get a malicious document or input into the agent's context (e.g., via RAG ingestion) — no direct tool access is required — to reach credential stores and potentially achieve remote code execution across every downstream application built on the vulnerable framework version.
Poisoned documents/inputs delivered to an agent's memory or RAG pipeline trigger insecure deserialization when the framework saves/reloads state, without the attacker needing direct tool invocation; also includes SSRF and sandbox-escape paths.
LangChain, CrewAI, Microsoft Agent Framework, Google ADK (Agent Development Kit)
Update to patched LangChain versions addressing CVE-2025-68664 (LangGrinch); Microsoft paid a bug bounty and fixed its issue (no CVE, framework was pre-GA); Google did not fully fix or CVE its ADK finding — restrict ADK's built-in dev assistant HTTP API exposure. Sandbox document parsers and limit IAM permissions granted to agent service accounts.
Security Point Break — Black Hat 2026: Old-School Bugs Crack Open AI Agent FrameworksThe Register — Prompt injection isn't the bug, AI agent frameworks are
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →