MCP Observatory
5m ago Tracked 39,510 Last 5m ago 24h 3,139
github Go analyzed · update queued 4b7f0c9

julien040/anyquery

github

One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.

maintainer
julien040
license
NOASSERTION
first seen
2026-06-01
last seen
2026-08-06
releases · 30d
1
short id
risk 60/100 · heuristic grade
D high
  • vulnerabilities attested + 50
  • capability exposure inferred + 18
  • 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.

graded 9m ago · see ecosystem CVEs →

risk trajectory 3 movements
  • B · 28 → D · 60
  • A · 10 → B · 28
  • A · 13 → A · 10
capability exposure grade factor +18
Inferred surface — each links to servers holding it:
vulnerabilities 12 CVEs · grade factor +50
CRITICAL
Arbitrary File Write (AFW) which could lead to Remote Code Execution (RCE) via Unrestricted ATTACH … CVE-2026-50006 affects ["<= 0.4.4"]
CRITICAL
AppleScript/JXA Code Injection via Unescaped URL in macOS plugins (Brave, Chrome, Edge, Reminders, … CVE-2026-47252 affects ["<= 0.1.2","<= 0.1.2","<= 0.1.2","<= 0.1.1","<= 0.1.1"]
HIGH
Remote query files executed through anyquery run can invoke local shell commands via dot commands affects ["<=0.4.6"]
HIGH
Server-mode sandbox arbitrary file write via ATTACH / VACUUM INTO with `?mode=memory&mode=rwc` affects ["0.4.6"]
HIGH
Unauthenticated Remote Query Execution via GPT Tunnel API affects ["<= 0.4.0"]
HIGH
Path Traversal in `clear_plugin_cache` Allows Arbitrary Directory Deletion CVE-2026-47253 affects ["<= 0.4.4"]
HIGH
Local File Read (LFR) via Unrestricted SQLite Virtual Table Modules in Server Mode CVE-2026-54629 affects ["<= 0.4.4"]
HIGH
Server-Side Request Forgery (SSRF) via Unrestricted SQLite Virtual Table Modules in Server Mode CVE-2026-54628 affects ["<= 0.4.4"]
HIGH
Unauthenticated HTTP API Endpoints (v0.4.3) EPSS 0% CVE-2025-61679 affects ["<=0.4.3"]
LOW
Dev-mode UDFs bypass server sandbox denylist enabling unauthenticated filesystem oracle (conditiona… affects [">= 0.4.5, <= 0.4.6"]
MEDIUM
Incomplete fix of GHSA-j4wj-p47h-f9cc - a third file-URI shape (file::http://host/abs/path forced g… affects ["<= 0.4.6"]
MEDIUM
Path Traversal: sandbox can be bypassed via file URI parsing affects ["<=0.4.5"]
tool safety all quiet

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

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

analyzed commit 4b7f0c9 · analyzer v30 · 3d ago

skills & prompt files 1

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:julien040/anyquery/badge.svg)](https://mcpobservatory.com/servers/github:julien040/anyquery/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 julien040.