Skip to content

Vendor

fastgpt vulnerabilities

14 published CVES affecting fastgpt, from public sources (CVE.org, NVD, CISA KEV, FIRST EPSS, OSV).

Total
14
Critical
4
High
2
Medium
8
Low
0
Unscored
0
CISA KEV
0
Atom feed of fastgpt alerts

Products

Latest fastgpt CVEs

Newest publication first

  1. HighCVSS 7.7 EPSS 0.29%

    FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without v...

  2. MediumCVSS 6.3 EPSS 0.35%

    FastGPT is an AI Agent building platform. In 4.14.7 and earlier, FastGPT's Python Sandbox (fastgpt-sandbox) includes guardrails intended to prevent file writes (static detection + seccomp). These guardrails are bypassable by remapping stdout (fd 1) to an arbitrary writable file d...

  3. MediumCVSS 6.9 EPSS 0.12%

    FastGPT is an AI Agent building platform. Due to the fact that FastGPT's web page acquisition nodes, HTTP nodes, etc. need to initiate data acquisition requests from the server, there are certain security issues. In addition to implementing internal network isolation in the deplo...

  4. MediumCVSS 6.9 EPSS 0.24%

    FastGPT is an AI Agent building platform. Prior to version 4.11.1, in the workflow file reading node, the network link is not security-verified, posing a risk of SSRF attacks. This issue has been patched in version 4.11.1.

  5. CriticalCVSS 9.9 EPSS 0.49%

    FastGPT is an open-source project that provides a platform for building, deploying, and operating AI-driven workflows and conversational agents. The Sandbox container (fastgpt-sandbox) is a specialized, isolated environment used by FastGPT to safely execute user-submitted or dyna...

  6. CVE-2025-27600 FastGPT SSRF

    Published
    MediumCVSS 6.9 EPSS 0.27%

    FastGPT is a knowledge-based platform built on the LLMs. Since the web crawling plug-in does not perform intranet IP verification, an attacker can initiate an intranet IP request, causing the system to initiate a request through the intranet and potentially obtain some private da...

Sources: CVE.org, NVD, CISA KEV, FIRST EPSS, OSV and public exploit-reference metadata. Product matching comes from the published CVE records. A proof-of-concept means public code exists; it is not evidence of exploitation.