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-/. 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.
CVE-2026-61643
MEDIUMPre-NVD 5.95.9
EchelonGraph scoreLOW confidence
This medium-severity CVE scores 5.9 under the CNA's CVSS (NVD's own analysis pending). EPSS exploit-prediction score not yet available (the EPSS model rescores nightly; freshly-published CVEs typically appear within 48 hours). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
Triggered by: NVD CVSS baseline
Sources: cna:github_m
5.9
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
- Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS: —CVSS: 5.9Exploit: NoneExposed: 0
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 5.9
- EG Score
- 5.9(low)
- EPSS
- —
- KEV
- Not listed
Published
July 15, 2026
Last Modified
July 15, 2026
Advisory Details (2)
Auto-updated Jul 15, 2026🔬 Proof of concept available. Patch available. Sources: github_release, github.
github Patch Available🟡 PoC Available
FastGPT: workflow runtime can execute another user's private HTTP toolset · Advisory · labring/FastGPT · GitHub
https://github.com/labring/FastGPT/security/advisories/GHSA-93r3-wqq3-c5chgithub_release Patch Available
v4.15.0-beta5
Patch available: labring/FastGPT v4.15.0-beta5 (pre-release)
https://github.com/labring/FastGPT/releases/tag/v4.15.0-beta5Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 2× in last 7d / 2× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-07-15 17:29 UTCEG score recompute
- 2026-07-15 17:28 UTCMITRE cvelistV5first tracked
Related CVEs(same CWE)
Same CWE
10 shownCWE-863
Frequently asked(4)
What is CVE-2026-61643?
CVE-2026-61643 is a medium vulnerability published on July 15, 2026. 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-<victimtoolsetappid>/<toolname>. The normal toolset routes…
When was CVE-2026-61643 disclosed?
CVE-2026-61643 was first published in the National Vulnerability Database on July 15, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
What is the CVSS score of CVE-2026-61643?
CVE-2026-61643 has a CVSS v3 base score of 5.9 (NVD). The EG score is currently aggregating — additional source signals are being incorporated as they become available..
How do I remediate CVE-2026-61643?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-61643, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2026-61643
Is Your Infrastructure Affected by CVE-2026-61643?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.