langchain-ai langchain
8 published vulnerabilities name this product.
As the CNAs write it in their CVE records (vendor and product); the versions are theirs.
| CVE | Vulnerable versions | Title | Severity | Published | EPSS | Exploitation |
|---|---|---|---|---|---|---|
| CVE-2026-55443 | < 1.3.9 | LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders | MEDIUM 5.5 | 0.2 % | ||
| CVE-2026-44843 | < 0.3.85 ; >= 1.0.0a1, < 1.3.3 | LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists | HIGH 8.2 | 0.4 % | ||
| CVE-2026-40087 | < 0.3.83 ; >= 1.0.0a1, < 1.2.28 | LangChain has incomplete f-string validation in prompt templates | MEDIUM 5.3 | 0.3 % | ||
| CVE-2026-34070 | < 1.2.22 | LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions | HIGH 7.5 | 1.4 % | ||
| CVE-2026-26013 | < 1.2.11 | LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages | LOW 3.7 | 0.4 % | ||
| CVE-2024-58340 | ≤ 0.3.1 | LangChain <= 0.3.1 MRKLOutputParser ReDoS | HIGH 8.7 | 0.5 % | ||
| CVE-2025-68664 | >= 1.0.0, < 1.2.5 ; < 0.3.81 | LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs | CRITICAL 9.3 | 43 % | ||
| CVE-2025-65106 | >= 1.0.0, < 1.0.7 ; < 0.3.80 | LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates | HIGH 8.3 | 0.5 % |