MCP Observatory
github analyzed e391d9c

saajunaid/junai

github

junai is 'Just Un-AI' routing with full AI power. Your agents stay smart. Your pipeline stays predictable. Deterministic agent pipeline for VS Code + GitHub Copilot. A Python state machine routes 23 specialised AI agents through 9 stages — no hallucinated routing, git-blameable transitions.

maintainer
saajunaid
license
NOASSERTION
first seen
2026-06-08
last seen
2026-06-12
releases · 30d
0
short id
risk 46/100 · heuristic grade
C elevated
  • capability exposureinferred+26
  • recent driftinferred+20

inferred

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 2 movements
  • C · 58 → C · 46
  • C · 50 → C · 58
capability exposure grade factor +26
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

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 e391d9c · analyzer v18 · 3h ago

skills & prompt files 183

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:saajunaid/junai/badge.svg)](https://mcpobservatory.com/servers/github:saajunaid/junai/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 saajunaid.