github Rust analyzed f171715 unconfirmed MCP

noviqtechnologies/agentwall

github

Vexa AgentWall is a full egress proxy and security gateway for AI agents operating over MCP, HTTP, HTTPS, and WebSocket connections. It provides organizations with a default-deny control plane to intercept, sandbox, audit, and actively block unauthorized agent tool calls and data exfiltration attempts.

maintainer
noviqtechnologies
license
Apache-2.0
first seen
2026-06-12
last seen
2026-08-11
releases · 30d
13
short id
risk 39/100 · heuristic grade
C elevated inferred analyzer v33 (current)
  • capability exposure inferred + 10
  • recent drift inferred + 20
  • tool safety inferred + 12
  • trust mitigators mixed − 3

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 1m ago · see ecosystem CVEs →

risk trajectory 4 movements
  • C · 35 C · 39
  • B · 29 C · 35
  • B · 21 B · 29
  • A · 0 B · 21
capability exposure grade factor +10
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12
  1. high dangerous code

    committed secret: AWS access key id, Anthropic key, private key

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

analyzed commit f171715 · analyzer v33 · 3d ago

danger signals6

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