Read the docs
TI-2026-44147 Aliases CVE-2026-61643

FastGPT: workflow runtime can execute another user's private HTTP toolset

Priority MEDIUM 60CWE-863Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
High
Impact type
Security bypass
Confidentiality · integrity · availability
Low · High · None
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA. Impact type from CWE-863.

Summary

FastGPT is a knowledge-based AI application platform. From 4.14.17 until 4.15.0-beta5, an authenticated FastGPT user can save a workflow node that points to another user's private HTTP toolset by using a crafted saved tool id such as http-<victim_toolset_app_id>/<tool_name>. The normal toolset routes deny access, but the workflow save and runtime path did not apply the same authorization check to the referenced toolset, allowing /api/v2/chat/completions to resolve the saved reference and execute the victim-owned HTTP tool. This issue is fixed in version 4.15.0-beta5.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00193 9th percentileScored 2026-11-07
Fix Fixed FastGPT (labring): 4.15.0-beta5

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
labringFastGPT4.14.17 to before 4.15.0-beta54.15.0-beta5Patch availableCNA
  • FastGPT Vendorlabring Affected 4.14.17 to before 4.15.0-beta5 Fixed in 4.15.0-beta5 Patch available CNA

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
cpe:2.3:a:fastgpt:fastgpt:*:*:*:*:*:*:*:*——Fastgpt
  • cpe:2.3:a:fastgpt:fastgpt:*:*:*:*:*:*:*:* Versions — — ·Fastgpt

Remediation

  • Fix · CNA FastGPT (labring) Fixed in 4.15.0-beta5

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-61643

References

Other 2

  • TI-2026-30610 FastGPT: Unauthenticated Remote Code Execution (RCE) via code-server Misconfiguration in agent-sandbox CVSS 3.1CRITICAL 9.8
  • TI-2026-48466 FastGPT: Unauthenticated WeChat channel hijack and denial of service via shareId-only authorization CVSS 4.0CRITICAL 9.3
  • TI-2026-44161 FastGPT: Unauthenticated cross-tenant data access via forgeable plugin-invoke JWT (default INVOKE_TOKEN_SECRET='token') CVSS 4.0HIGH 8.8
  • TI-2026-44148 Incorrect authorization in labring FastGPT CVSS 3.1HIGH 7.7
  • TI-2026-39440 FastGPT: SSRF in HTTP-tool OpenAPI schema importer via SwaggerParser $ref (bypasses the isInternalAddress guard) CVSS 3.1HIGH 7.7
  • TI-2026-30646 FastGPT: Uncontrolled Resource Consumption leading to Sandbox Exhaustion CVSS 4.0MEDIUM 6.3
See all 18 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences