MCP Observatory
3m ago Tracked 59,460 Last 3m ago 24h 2,456
npm JavaScript analyzed 5.217.0

agent-afk

v5.217.0
npm

Open-source coding-agent harness you can actually change — own the loop (prompts, gates, routing, skills, terminal states), use any model, run long tasks while you're away.

maintainer
griffinwork40
licence
Apache-2.0
first seen
2026-06-08
last seen
2026-09-17
releases · 30d
423
short id
risk 19/100 · heuristic grade
B low inferred analyzer v33 (current)
  • capability exposure inferred + 22
  • supply-chain attested + 6
  • trust mitigators mixed − 9

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.

grade last moved 2d ago · see ecosystem CVEs →

risk trajectory 8 movements
  • B · 29 → B · 19
  • B · 19 → B · 29
  • B · 32 → B · 19
  • A · 13 → B · 32
  • B · 28 → A · 13
  • C · 47 → B · 28
  • C · 53 → C · 47
  • C · 47 → C · 53
capability exposure grade factor +22
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 npm-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v5.217.0 · analyzer v33 · 1h ago

skills & prompt files 19

danger signals2

  • suspicious endpoint api.telegram.org expected for this server's purpose package/dist/cli.mjs :433 =y(()=>{"use strict";Hf();QP();F();Oxe="https://api.telegram.org"});function $xe(e=Ou){return async(t,n)=>{if(!t||typeof t!="object")return{content:"Invalid input: expected an object",isError:!0};let
  • suspicious endpoint api.telegram.org expected for this server's purpose package/dist/index.mjs :277 c=m(()=>{"use strict";sm();fe();P();U1="https://api.telegram.org"});function B1(t=Hs){return async(e,n)=>{if(!e||typeof e!="object")return{content:"Invalid input: expected an object",isError:!0};let r
other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:agent-afk/badge.svg)](https://mcpobservatory.com/servers/npm:agent-afk/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 griffinwork40.