LangChain Community SSRF vulnerability exists in RequestsToolkit component
CVE-2025-2828 · GHSA-h5gc-rm8j-5gpr · published 2025-06-23 · updated 2025-07-17
- Severity
- High
- CVSS score
- 8.4
- Chance of exploitation (EPSS)
- 21.0%
- Fixed in
- 0.0.28
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchaincommunity.agenttoolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs because the toolkit does not enforce restrictions on requests to remote internet addresses, allowing it to also access local addresses. As a result, an attacker could exploit this flaw to perform port scans, access local services, retrieve instance metadata from cloud environments (e.g., Azure, AWS), and interact with servers on the local network. This issue has been fixed in version 0.0.28.
Upgrade langchain-community to 0.0.28 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.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| langchain-community | PyPI | < 0.0.28 | 0.0.28 |
- CriticalMLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebindingmlflowExploited
- Critical@zereight/mcp-gitlab Vulnerable to Server-Side Request Forgery@zereight/mcp-gitlab
- CriticalSSRF + LLM API key exfiltration via user-controlled basepath / baseUrl in 8 chat-model nodesflowise, flowise-components
- CriticalLocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLsgithub.com/mudler/LocalAI
- CriticalFastMCP OpenAPI Provider has an SSRF & Path Traversal Vulnerabilityfastmcp
- CriticalBentoML SSRF Vulnerability in File Upload Processingbentoml
- HighLangchain Community Vulnerable to XML External Entity (XXE) Attackslangchain-community
- HighLangChain pickle deserialization of untrusted datalangchain-community
- MediumDenial of service in langchain-communitylangchain, langchain-community
- MediumServer-Side Request Forgery in langchain-community.retrievers.web_research.WebResearchRetrieverlangchain-community
- LowLangchain SQL Injection vulnerabilitylangchain, langchain-community
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.