CVE-2025-65106

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.

Context

A template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes.

Templates allow attribute access (.) and indexing ([]) but not method invocation (()).

The combination of attribute access and indexing may enable exploitation depending on which objects are passed to templates. When template variables are simple strings (the common case), the impact is limited. However, when using MessagesPlaceholder with chat message objects, attackers can traverse through object attributes and dictionary lookups (e.g., __globals__) to reach sensitive data such as environment variables.

The vulnerability specifically requires that applications accept template strings (the structure) from untrusted sources, not just template variables (the data). Most applications either do not use templates or else use hardcoded templates and are not vulnerable.

Affected Components

• langchain-core package
• Template formats:
  • F-string templates (template_format="f-string") - Vulnerability fixed
  • Mustache templates (template_format="mustache") - Defensive hardening
  • Jinja2 templates (template_format="jinja2") - Defensive hardening

Impact

Attackers who can control template strings (not just template variables) can:

• Access Python object attributes and internal properties via attribute traversal
• Extract sensitive information from object internals (e.g., __class__, __globals__)
• Potentially escalate to more severe attacks depending on the objects passed to templates

Attack Vectors

1. F-string Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate

malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{msg.__class__.__name__}")],
    template_format="f-string"
)

# Note that this requires passing a placeholder variable for "msg.__class__.__name__".
result = malicious_template.invoke({"msg": "foo", "msg.__class__.__name__": "safe_placeholder"})
# Previously returned
# >>> result.messages[0].content
# >>> 'str'

2. Mustache Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.__class__.__name__}}")],
    template_format="mustache"
)

result = malicious_template.invoke({"question": msg})
# Previously returned: "HumanMessage" (getattr() exposed internals)

3. Jinja2 Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.parse_raw}}")],
    template_format="jinja2"
)

result = malicious_template.invoke({"question": msg})
# Could access non-dunder attributes/methods on objects

Root Cause

1. F-string templates: The implementation used Python's string.Formatter().parse() to extract variable names from template strings. This method returns the complete field expression, including attribute access syntax:

   from string import Formatter
   
   template = "{msg.__class__} and {x}"
   print([var_name for (_, var_name, _, _) in Formatter().parse(template)])
   # Returns: ['msg.__class__', 'x']
   

   The extracted names were not validated to ensure they were simple identifiers. As a result, template strings containing attribute traversal and indexing expressions (e.g., {obj.__class__.__name__} or…

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.

Context

A template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes.

Templates allow attribute access (.) and indexing ([]) but not method invocation (()).

The combination of attribute access and indexing may enable exploitation depending on which objects are passed to templates. When template variables are simple strings (the common case), the impact is limited. However, when using MessagesPlaceholder with chat message objects, attackers can traverse through object attributes and dictionary lookups (e.g., __globals__) to reach sensitive data such as environment variables.

The vulnerability specifically requires that applications accept template strings (the structure) from untrusted sources, not just template variables (the data). Most applications either do not use templates or else use hardcoded templates and are not vulnerable.

Affected Components

• langchain-core package
• Template formats:
  • F-string templates (template_format="f-string") - Vulnerability fixed
  • Mustache templates (template_format="mustache") - Defensive hardening
  • Jinja2 templates (template_format="jinja2") - Defensive hardening

Impact

Attackers who can control template strings (not just template variables) can:

• Access Python object attributes and internal properties via attribute traversal
• Extract sensitive information from object internals (e.g., __class__, __globals__)
• Potentially escalate to more severe attacks depending on the objects passed to templates

Attack Vectors

1. F-string Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate

malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{msg.__class__.__name__}")],
    template_format="f-string"
)

# Note that this requires passing a placeholder variable for "msg.__class__.__name__".
result = malicious_template.invoke({"msg": "foo", "msg.__class__.__name__": "safe_placeholder"})
# Previously returned
# >>> result.messages[0].content
# >>> 'str'

2. Mustache Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.__class__.__name__}}")],
    template_format="mustache"
)

result = malicious_template.invoke({"question": msg})
# Previously returned: "HumanMessage" (getattr() exposed internals)

3. Jinja2 Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.parse_raw}}")],
    template_format="jinja2"
)

result = malicious_template.invoke({"question": msg})
# Could access non-dunder attributes/methods on objects

Root Cause

1. F-string templates: The implementation used Python's string.Formatter().parse() to extract variable names from template strings. This method returns the complete field expression, including attribute access syntax:

   from string import Formatter
   
   template = "{msg.__class__} and {x}"
   print([var_name for (_, var_name, _, _) in Formatter().parse(template)])
   # Returns: ['msg.__class__', 'x']
   

   The extracted names were not validated to ensure they were simple identifiers. As a result, template strings containing attribute traversal and indexing expressions (e.g., {obj.__class__.__name__} or…

Context

A template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes.

Templates allow attribute access (.) and indexing ([]) but not method invocation (()).

The combination of attribute access and indexing may enable exploitation depending on which objects are passed to templates. When template variables are simple strings (the common case), the impact is limited. However, when using MessagesPlaceholder with chat message objects, attackers can traverse through object attributes and dictionary lookups (e.g., __globals__) to reach sensitive data such as environment variables.

The vulnerability specifically requires that applications accept template strings (the structure) from untrusted sources, not just template variables (the data). Most applications either do not use templates or else use hardcoded templates and are not vulnerable.

Affected Components

• langchain-core package
• Template formats:
  • F-string templates (template_format="f-string") - Vulnerability fixed
  • Mustache templates (template_format="mustache") - Defensive hardening
  • Jinja2 templates (template_format="jinja2") - Defensive hardening

Impact

Attackers who can control template strings (not just template variables) can:

• Access Python object attributes and internal properties via attribute traversal
• Extract sensitive information from object internals (e.g., __class__, __globals__)
• Potentially escalate to more severe attacks depending on the objects passed to templates

Attack Vectors

1. F-string Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate

malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{msg.__class__.__name__}")],
    template_format="f-string"
)

# Note that this requires passing a placeholder variable for "msg.__class__.__name__".
result = malicious_template.invoke({"msg": "foo", "msg.__class__.__name__": "safe_placeholder"})
# Previously returned
# >>> result.messages[0].content
# >>> 'str'

2. Mustache Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.__class__.__name__}}")],
    template_format="mustache"
)

result = malicious_template.invoke({"question": msg})
# Previously returned: "HumanMessage" (getattr() exposed internals)

3. Jinja2 Template Injection

Before Fix:

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import HumanMessage

msg = HumanMessage("Hello")

# Attacker controls the template string
malicious_template = ChatPromptTemplate.from_messages(
    [("human", "{{question.parse_raw}}")],
    template_format="jinja2"
)

result = malicious_template.invoke({"question": msg})
# Could access non-dunder attributes/methods on objects

Root Cause

1. F-string templates: The implementation used Python's string.Formatter().parse() to extract variable names from template strings. This method returns the complete field expression, including attribute access syntax:

   from string import Formatter
   
   template = "{msg.__class__} and {x}"
   print([var_name for (_, var_name, _, _) in Formatter().parse(template)])
   # Returns: ['msg.__class__', 'x']
   

   The extracted names were not validated to ensure they were simple identifiers. As a result, template strings containing attribute traversal and indexing expressions (e.g., {obj.__class__.__name__} or…

Root has patched CVE-2025-65106 in the langchain-core package for Root:PyPI. Multiple fixed versions available.