MCP Observatory
npm analyzed 2.131.1

nexus-agents

v2.131.1
npm

Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, immutable audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode

maintainer
williamzujkowski
license
MIT
first seen
2026-06-04
last seen
2026-06-11
releases · 30d
153
short id
risk61/100 · heuristic grade
D high
  • capability exposureinferred+35
  • inherited (deps)attested+15
  • tool safetyinferred+14
  • supply-chainattested+6
  • trust mitigatorsmixed−9

attestedinferredmixed

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 8m ago · see ecosystem CVEs →

risk trajectory1 movements
  • D · 72 → D · 61
capability exposuregrade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities0 CVEs

no known CVEs for this server.

inherited (deps) · grade factor +15

inherited via dependencies4
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @modelcontextprotocol/sdk · 1 hop CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @modelcontextprotocol/sdk · 1 hop CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @modelcontextprotocol/sdk · 1 hop CVE-2025-66414 fixed in 1.24.0
LOW
Vercel’s AI SDK's filetype whitelists can be bypassed when uploading files via ai · 1 hop CVE-2025-48985 fixed in 5.0.52
tool safety2 findings · grade factor +14
  1. highexfiltration combosearch_codebase

    single tool reads + sends: fs, net

  2. lowexfiltration comboresearch_query

    single tool reads + sends: net, db

other grade factorsevidence elsewhere
embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:nexus-agents/badge.svg)](https://mcpobservatory.com/servers/npm:nexus-agents/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 williamzujkowski.