https://db.gcve.eu Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Thu, 01 Oct 2026 12:31:43 +0000 https://db.gcve.eu/vuln/cve-2025-65106 <p><strong>Affected:</strong> langchain-ai langchain</p> <p>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&#39;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.</p> <p><strong>Affected:</strong> langchain-ai langchain</p> <p>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&#39;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.</p> https://db.gcve.eu/vuln/cve-2025-65106 https://db.gcve.eu/vuln/ghsa-6qv9-48xg-fc7f <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Context</p> <p>A template injection vulnerability exists in LangChain&#39;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.</p> <p>Templates allow attribute access (`.`) and indexing (`[]`) but not method invocation (`()`).</p> <p>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.</p> <p>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.</p> <p>## Affected Components</p> <p>- `langchain-core` package - Template formats: - F-string templates (`template_format=&#34;f-string&#34;`) - **Vulnerability fixed** - Mustache templates (`template_format=&#34;mustache&#34;`) - **Defensive hardening** - Jinja2 templates (`template_format=&#34;jinja2&#34;`) - **Defensive hardening**</p> <p>### Impact Attackers who can control template s…</p> <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Context</p> <p>A template injection vulnerability exists in LangChain&#39;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.</p> <p>Templates allow attribute access (`.`) and indexing (`[]`) but not method invocation (`()`).</p> <p>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.</p> <p>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.</p> <p>## Affected Components</p> <p>- `langchain-core` package - Template formats: - F-string templates (`template_format=&#34;f-string&#34;`) - **Vulnerability fixed** - Mustache templates (`template_format=&#34;mustache&#34;`) - **Defensive hardening** - Jinja2 templates (`template_format=&#34;jinja2&#34;`) - **Defensive hardening**</p> <p>### Impact Attackers who can control template s…</p> https://db.gcve.eu/vuln/ghsa-6qv9-48xg-fc7f https://db.gcve.eu/vuln/pysec-2026-1518 <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Context</p> <p>A template injection vulnerability exists in LangChain&#39;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.</p> <p>Templates allow attribute access (`.`) and indexing (`[]`) but not method invocation (`()`).</p> <p>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.</p> <p>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.</p> <p>## Affected Components</p> <p>- `langchain-core` package - Template formats: - F-string templates (`template_format=&#34;f-string&#34;`) - **Vulnerability fixed** - Mustache templates (`template_format=&#34;mustache&#34;`) - **Defensive hardening** - Jinja2 templates (`template_format=&#34;jinja2&#34;`) - **Defensive hardening**</p> <p>### Impact Attackers who can control template s…</p> <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Context</p> <p>A template injection vulnerability exists in LangChain&#39;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.</p> <p>Templates allow attribute access (`.`) and indexing (`[]`) but not method invocation (`()`).</p> <p>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.</p> <p>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.</p> <p>## Affected Components</p> <p>- `langchain-core` package - Template formats: - F-string templates (`template_format=&#34;f-string&#34;`) - **Vulnerability fixed** - Mustache templates (`template_format=&#34;mustache&#34;`) - **Defensive hardening** - Jinja2 templates (`template_format=&#34;jinja2&#34;`) - **Defensive hardening**</p> <p>### Impact Attackers who can control template s…</p> https://db.gcve.eu/vuln/pysec-2026-1518