Answer in brief
CVE-2026-34070 records a High severity (CVSS 7.5) vulnerability in LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions. The current sources do not mark it as known exploited. The current feed maps langchain-ai/langchain (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
Answer in brief
CVE-2026-34070 records a High severity (CVSS 7.5) vulnerability in LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions. The current sources do not mark it as known exploited. The current feed maps langchain-ai/langchain (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps langchain-ai/langchain (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| langchain-ai/langchaingeneric | < 1.2.22 | Not reported |
Published upstream
Mar 31, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Jul 15, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jul 10, 2026
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 injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
Quoted source text, attributed separately from HOL analysis.
CVSS is 7.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps langchain-ai/langchain (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| langchain-ai/langchaingeneric | < 1.2.22 | Not reported |
Published upstream
Mar 31, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Jul 15, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jul 10, 2026
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 injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
Quoted source text, attributed separately from HOL analysis.