MCP Observatory
4m ago Tracked 39,516 Last 4m ago 24h 3,135
npm JavaScript analyzed 13.15.0

claude-mem

v13.15.0
npm

Memory compression system for Claude Code - persist context across sessions

maintainer
thedotmack
license
Apache-2.0
first seen
2026-05-22
last seen
2026-08-14
releases · 30d
9
short id
risk 39/100 · heuristic grade
C elevated
  • capability exposure inferred + 35
  • tool safety inferred + 12
  • trust mitigators mixed − 8

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 5m ago · see ecosystem CVEs →

risk trajectory 4 movements
  • C · 54 → C · 39
  • C · 55 → C · 54
  • C · 54 → C · 55
  • C · 41 → C · 54
capability exposure grade factor +35
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

    dynamic exec: new Function() · suspicious bundled script in 1 file(s)

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

analyzed v13.15.0 · analyzer v32 · 13h ago

skills & prompt files 20

danger signals8

  • dynamic code execution new Function() package/dist/npx-cli/index.js :1134 r(){if(r.count++>KU){let n;try{n=t.read=new Function("r","return function(){return "+(je.freezeData?"Object.freeze":"")+"({"+t.map(o=>o==="__proto__"?"__proto_:r()":joe.test(o)?o+":r()":"["+JSON.strin
  • suspicious endpoint us.i.posthog.com (telemetry) expected for this server's purpose package/dist/npx-cli/index.js :101 32N9qEiU6qhutZEiu6LLfRpXfTbLM9MLaG",I3="https://us.i.posthog.com";_3=["version","os","os_version","is_wsl","arch","runtime","locale","ide","provider","runtime_mode","install_method","claude_code_versi
  • suspicious endpoint api.telegram.org package/openclaw/src/index.ts :468 const response = await fetch(`https://api.telegram.org/bot${botToken}/sendMessage`, {
  • suspicious endpoint us.i.posthog.com (telemetry) expected for this server's purpose package/plugin/scripts/transcript-watcher.cjs :16 32N9qEiU6qhutZEiu6LLfRpXfTbLM9MLaG",Yn="https://us.i.posthog.com";function tr(){return process.env.CLAUDE_MEM_TELEMETRY_KEY||Gn}function rr(){return process.env.CLAUDE_MEM_TELEMETRY_HOST||Yn}var Kn=["
  • suspicious endpoint us.i.posthog.com (telemetry) expected for this server's purpose package/plugin/scripts/worker-service.cjs :28 2N9qEiU6qhutZEiu6LLfRpXfTbLM9MLaG",Sde="https://us.i.posthog.com";Ede=["version","os","os_version","is_wsl","arch","runtime","locale","ide","provider","runtime_mode","install_method","claude_code_vers
  • suspicious endpoint api.telegram.org package/plugin/skills/mode-creator/scripts/configure-telegram.mjs :107 const response = await fetch(`https://api.telegram.org/bot${token}/${method}`, {
  • suspicious endpoint t.me package/plugin/skills/mode-creator/scripts/configure-telegram.mjs :170 console.log(`Open https://t.me/${bot.username}, press Start, and send any message.`);
  • suspicious bundled script suspicious bundled script package/openclaw/install.sh :419 if ! curl -fsSL https://bun.sh/install | bash; then
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:claude-mem/badge.svg)](https://mcpobservatory.com/servers/npm:claude-mem/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 thedotmack.