LangChain has incomplete f-string validation in prompt templates

Summary

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 enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate those expressions during formatting. Second, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. In this pattern, the nested replacement field appears in the format specifier rather than in the top-level field name. As a result, earlier validation based on parsed field names did not reject the template even though Python formatting would still attempt to resolve the nested expression at runtime. This vulnerability is fixed in 0.3.84 and 1.2.28.

Timeline

1. Apr 9, 2026, 7:34 PM UTCCVE published
2. Apr 14, 2026, 2:47 PM UTCCISA SSVC assessment

   Exploitation: none · Automatable: yes · Technical impact: partial

3. Apr 14, 2026, 2:48 PM UTCRecord last updated

Affected versions

• langchain-ai langchain

  fixed in 0.3.83; From 1.0.0a1 · fixed in 1.2.28

• langchain-corePyPI

  fixed in 0.3.84; From 1.0.0a1 · fixed in 1.2.28

• langchain-corePyPI

  fixed in 0.3.84

• langchain-corePyPI

  From 1.0.0a1 · fixed in 1.2.28

References 7