UTC
Medium

LangChain has incomplete f-string validation in prompt templates

CVE-2026-40087 · GHSA-926x-3r5x-gfhw · published 2026-04-08 · updated 2026-04-10

Severity
Medium
CVSS score
5.3
Chance of exploitation (EPSS)
0.27%
Fixed in
1.2.28
  • Exploitation No known exploitation
  • Automatable Yes
  • Technical impact Partial
  • CISA SSVC
What it is

The direct issue in DictPromptTemplate and ImagePromptTemplate allowed attribute access and indexing expressions to survive template construction and then be evaluated during formatting. When richer Python objects were passed into formatting, this could expose internal fields or nested data to prompt output, model context, or logs. The nested format-spec issue is narrower in scope. It bypassed the intended validation rules for f-string templates, but in simple cases it results in an invalid format specifier error rather than direct disclosure. Accordingly, its practical impact is lower than that of direct top-level attribute traversal. Overall, the practical severity depends on deployment.

What to do

Upgrade langchain-core to 1.2.28 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

The fix consists of two changes. First, LangChain now applies f-string safety validation consistently to DictPromptTemplate and ImagePromptTemplate, so templates containing attribute access or indexing expressions are rejected during construction and deserialization. Second, LangChain now rejects nested replacement fields inside f-string format specifiers. Concretely, LangChain validates parsed f-string fields and raises an error for: variable names containing attribute access or indexing syntax such as .

Affected
PackageRegistryAffectedFixed in
langchain-corePyPI< 0.3.830.3.84
langchain-corePyPI>= 1.0.0a1, < 1.2.281.2.28

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].