MCP Observatory
1m ago Tracked 58,273 Last 1m ago 24h 2,653
github TypeScript analyzed 64cdef2 deep scan · partial (261/4,578 files)

ThinkInAIXYZ/deepchat

github

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

maintainer
ThinkInAIXYZ
licence
Apache-2.0
first seen
2026-06-01
last seen
2026-09-15
releases · 30d
11
short id
risk 89/100 · heuristic grade
E critical inferred analyzer v33 (current)
  • vulnerabilities attested + 50
  • capability exposure inferred + 35
  • tool safety inferred + 12
  • trust mitigators mixed − 8

attested inferred mixed

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.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 3 movements
  • D · 77 → E · 89
  • B · 27 → D · 77
  • A · 0 → B · 27
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 7 CVEs · grade factor +50
CRITICAL
One-click Remote Code Execution through Custom URL Handling in DeepChat v0.3.0 EPSS 1% CVE-2025-55733 affects ["0.3.0"]
CRITICAL
Mermaid rendering has XSS leading to RCE EPSS 1% CVE-2025-58768 affects ["<=0.3.4"]
CRITICAL
Remote Code Execution (RCE) via Mermaid XSS EPSS 1% CVE-2025-67744 affects ["<= v0.5.2"]
CRITICAL
Cross-Site Scripting(XSS) escalate to Remote Code Execution(RCE) EPSS 1% CVE-2025-66222 affects ["<=0.5.0"]
CRITICAL
Incomplete XSS Fix Allows RCE EPSS 0% CVE-2025-66481 affects ["<=0.5.1"]
CRITICAL
Incomplete Fix for CVE-2025-55733 leads to Remote Code Execution via Markdown Links bypassing `isVa… EPSS 0% CVE-2026-43899 affects ["All current branches up to main (Incomplete fix for CVE-2025-55733)"]
CRITICAL
Persistent DOM XSS via HTML Entity Encoding in `<antArtifact>` SVG Rendering (Bypass of `svgSanitiz… EPSS 0% CVE-2026-43900 affects ["All untracked versions up to current standard."]
tool safety 1 findings · grade factor +12
  1. high dangerous code

    committed secret: OpenAI key · dynamic exec: constructor escape

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 64cdef2 · analyzer v33 · 5h ago

skills & prompt files 26

danger signals5

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