LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforc...
Product
@langchain langchain core vulnerabilities
4 published CVES affecting @langchain langchain core, from public sources (CVE.org, NVD, CISA KEV, FIRST EPSS, OSV).
- Total
- 4
- Critical
- 0
- High
- 2
- Medium
- 1
- Low
- 1
- Unscored
- 0
- CISA KEV
- 0
Latest @langchain langchain core CVEs
Newest publication first
-
MediumCVSS 5.3 EPSS 0.27%
-
CVE-2026-34070 LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions
PublishedHighCVSS 7.5 EPSS 1.5%LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path inj...
-
LowCVSS 3.7 EPSS 0.42%
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to t...
-
HighCVSS 8.2 EPSS 42.9% Public exploit
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing fre...
Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.