MCP Observatory
github not analyzable

lobehub/lobehub

github

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

maintainer
lobehub
license
NOASSERTION
first seen
2026-05-22
last seen
2026-06-14
releases · 30d
144
short id
risk47/100 · heuristic grade
C elevated

Source not yet analyzed — this grade rests on attested signals (CVEs, supply-chain) only. It is a floor: reading the code could raise it, not lower it.

  • vulnerabilitiesattested+50
  • trust mitigatorsmixed−3

attestedmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 11m ago · see ecosystem CVEs →

vulnerabilities14 CVEs · grade factor +50
CRITICAL
Cross-Site Scripting(XSS) escalate to Remote Code Execution(RCE) EPSS 0% CVE-2026-23733 affects ["<= v2.0.0-next.179"]
CRITICAL
Insufficient fix for GHSA-mxhq-xw3g-rphc (CVE-2024-32964) EPSS 6% CVE-2024-47066 affects ["<= v1.19.12"]
CRITICAL
【Critical】`/api/proxy` endpoint ssrf vulnerability in lobe-chat EPSS 73% CVE-2024-32964 affects ["<= v0.150.5"]
HIGH
【high】ssrf vulnerability in lobe-chat 1 EPSS 3% CVE-2024-32965 affects ["<= v0.150.1"]
MEDIUM
Unauthenticated SSRF in `/webapi/proxy` EPSS 0% CVE-2026-54157 affects ["=<v2.1.56"]
MEDIUM
Cross-Site Scripting(XSS) escalate to Remote Code Execution(RCE) EPSS 0% CVE-2026-42045 affects ["<=v2.1.47"]
MEDIUM
Unauthenticated authentication bypass on `webapi` routes via forgeable `X-lobe-chat-auth` header EPSS 0% CVE-2026-39411 affects ["<= 2.1.47"]
MEDIUM
Improper Authorization in Presigned Upload: User-controlled object key enables cross-namespace uploa… EPSS 0% CVE-2026-23835 affects ["<= 1.143.2"]
LOW
IDOR in Knowledge Base File Removal Allows Cross User File Deletion EPSS 0% CVE-2026-23522 affects ["<= v2.0.0-next.192"]
LOW
SSRF in lobehub/lobe-chat with native web fetch module EPSS 0% CVE-2025-62505 affects ["1.136.1"]
MEDIUM
Open Redirect in lobehub/lobe-chat EPSS 0% CVE-2025-59426 affects ["<1.130.0"]
MEDIUM
Remote Code Execution via XSS in Chat Messages in Lobe Chat Desktop EPSS 0% CVE-2025-59417 affects ["<v1.129.3"]
MEDIUM
Unexpected API Key Leak EPSS 0% CVE-2024-37895 affects ["<=0.162.24"]
MEDIUM
Unauthorized access to chat plugins EPSS 0% CVE-2024-24566 affects ["<= 0.122.3"]
tool safetyall quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:lobehub/lobehub/badge.svg)](https://mcpobservatory.com/servers/github:lobehub/lobehub/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of lobehub.