LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-3248 | Unauthenticated RCE in Langflow /api/v1/validate/code | 9.8 | 100% | KEVRansomwarePoC ×4 | KEV |
| CVE-2025-67644 | LangGraph SQLite Checkpoint: Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to… | 7.8 | 2% | PoC | |
| CVE-2025-68664 | Serialization Injection in LangChain Core dumps()/dumpd() Exposes Secrets | 8.2 | 43% | PoC ×2 | |
| CVE-2026-33017 | Unauthenticated RCE in Langflow AI Workflow Builder | 9.3 | 96% | KEVPoC ×6 | KEV |
| CVE-2026-34070 | LangChain: Multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without… | 7.5 | 1% | PoC |
From the original article
2 min read at thehackernews.com
Ravie Lakshmanan Mar 27, 2026 Vulnerability / Artificial Intelligence Cybersecurity researchers have disclosed three security vulnerabilities impacting LangChain and LangGraph that, if successfully exploited, could expose filesystem data, environment secrets, and conversation history.
By @TheHackersNews · thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.