MCP Observatory
npm analyzed 3.13.0

@neriros/ralphy

v3.13.0
npm

An iterative AI task execution framework. Orchestrates multi-phase autonomous work using Claude or Codex engines.

maintainer
rosneri
license
MIT
first seen
2026-05-22
last seen
2026-06-16
releases · 30d
36
short id
risk 19/100 · heuristic grade
B low
  • capability exposureinferred+4
  • recent driftinferred+12
  • tool safetyinferred+12
  • trust mitigatorsmixed−9

inferredmixed

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 16m ago · see ecosystem CVEs →

risk trajectory 1 movements
  • B · 31 → B · 19
capability exposure grade factor +4
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. highdangerous code

    dynamic exec: new Function()

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

analyzed v3.13.0 · analyzer v18 · 8h ago

danger signals1

  • dynamic code executionnew Function()package/dist/mcp/index.js:2893const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);
other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:@neriros/ralphy/badge.svg)](https://mcpobservatory.com/servers/npm:@neriros/ralphy/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 rosneri.