registry  /  freddie  /  0.0.125

freddie@0.0.125

Open JS agent harness built on pi-mono, floosie, xstate, and anentrypoint-design

AI Security Review

scanned 9d ago · by lpm-firewall-ai

No confirmed malicious attack surface is established. The package is an AI agent/CLI framework with user-invoked tools for shell execution, messaging, Home Assistant, LLM APIs, memory providers, and dashboard routes.

Static reason
High-risk behavior combination matched malicious policy.
Trigger
Explicit CLI use, dashboard/API use, or agent tool invocation after installation.
Impact
Can execute commands or send data to configured services when users enable/invoke those tools, but no unconsented install-time execution or credential exfiltration was found.
Mechanism
Plugin-based agent tools and service integrations
Rationale
The suspicious primitives are aligned with an agent harness and service-integration package and are activated by explicit user/runtime tool use, not by npm lifecycle or import-time stealth behavior. The scanner's credential-exfiltration hint on Home Assistant is a false positive because the token is sent as the required bearer credential to the configured Home Assistant API.
Evidence
package.jsonbin/freddie.jssrc/index.jsplugins/homeassistant_tool/handler.jsplugins/send_message/handler.jsplugins/platform-wecom_crypto/handler.jsplugins/bash/handler.jsplugins/code_execution/handler.js~/.freddie auth/config/session/state paths at runtimeproject files via explicit edit/patch/checkpoint tools at runtime
Network endpoints10
homeassistant.local:8123open.feishu.cnapi.spotify.com/v1api.telegram.orgdiscord.com/api/v10slack.com/apiapi.openrouter.aiapi.hunyuan.cloud.tencent.comapi.osv.dev/v1/queryraw.githubusercontent.com/AnEntrypoint/freddie-skills/main/index.json

Decision evidence

public snapshot
AI called this Clean at 86.0% confidence as Benign with low false-positive risk.
Evidence for block
  • Runtime includes user-invoked shell/code tools such as plugins/bash/handler.js and plugins/code_execution/handler.js.
  • Network integrations send configured tokens to their intended APIs when invoked, e.g. HASS_URL, Discord, Slack.
Evidence against
  • package.json has no preinstall/install/postinstall scripts; scripts are start/test/build-only.
  • bin/freddie.js only boots host and registers CLI commands; no hidden install-time mutation.
  • plugins/homeassistant_tool/handler.js uses HASS_TOKEN only as Authorization to HASS_URL/Home Assistant API.
  • plugins/send_message/handler.js dynamic import is enum-gated to fixed platform module paths.
  • plugins/platform-wecom_crypto/handler.js implements WeCom signature/decryption helpers; no outbound network or persistence.
  • Scans show network endpoints are named service integrations, LLM providers, local servers, or user-configured URLs.
Behavioral surface
Source
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShellWebSocket
Supply chain
HighEntropyStringsUrlStrings
Manifest
WildcardDependency
scanned 420 file(s), 534 KB of source, external domains: 127.0.0.1, api.byterover.com, api.hindsightai.com, api.honcho.dev, api.hunyuan.cloud.tencent.com, api.mem0.ai, api.moonshot.ai, api.moonshot.cn, api.nousresearch.com, api.openviking.com, api.osv.dev, api.retaindb.com, api.sgroup.qq.com, api.spotify.com, api.supermemory.ai, api.telegram.org, api.twilio.com, api.vercel.com, api.weixin.qq.com, api.x.ai, api.z.ai, app.daytona.io, cloudcode-pa.googleapis.com, discord.com, graph.facebook.com, homeassistant.local, html.duckduckgo.com, models.dev, oapi.dingtalk.com, oauth2.googleapis.com, open.bigmodel.cn, open.feishu.cn, openrouter.ai, qyapi.weixin.qq.com, raw.githubusercontent.com, serpapi.com, slack.com, www.apple.com, www.googleapis.com

Source & flagged code

3 flagged · loading source
plugins/send_message/handler.jsView file
19if (!mod) return { error: 'unknown platform: ' + platform } L20: const m = await import(mod) L21: const cls = Object.values(m)[0]
Medium
Dynamic Require

Package source references dynamic require/import behavior.

plugins/send_message/handler.jsView on unpkg · L19
plugins/platform-wecom_crypto/handler.jsView file
6export function decryptMsg(encryptedB64, encodingAesKey) { L7: const aesKey = Buffer.from(encodingAesKey + '=', 'base64') L8: const iv = aesKey.slice(0, 16)
Low
Weak Crypto

Package source references weak cryptographic algorithms.

plugins/platform-wecom_crypto/handler.jsView on unpkg · L6
plugins/homeassistant_tool/handler.jsView file
3toolset: 'core', L4: schema: { name: 'homeassistant_tool', description: 'Read state or call a service on Home Assistant.', parameters: { type: 'object', properties: { action: { type: 'string', enum: ['... L5: requiresEnv: ['HASS_TOKEN', 'HASS_URL'], L6: checkFn: () => Boolean(process.env.HASS_TOKEN), L7: handler: async ({ action, entity_id, domain, service, data = {} }) => { L8: const url = process.env.HASS_URL || 'http://homeassistant.local:8123' L9: const auth = { authorization: `Bearer ${process.env.HASS_TOKEN}` } L10: if (action === 'state') return await (await fetch(`${url}/api/states/${entity_id}`, { headers: auth })).json() L11: if (action === 'service') return await (await fetch(`${url}/api/services/${domain}/${service}`, { method: 'POST', headers: { ...auth, 'content-type': 'application/json' }, body: JS...
Critical
Credential Exfiltration

Source appears to send environment or credential material to an external endpoint.

plugins/homeassistant_tool/handler.jsView on unpkg · L3

Findings

1 Critical4 Medium5 Low
CriticalCredential Exfiltrationplugins/homeassistant_tool/handler.js
MediumDynamic Requireplugins/send_message/handler.js
MediumNetwork
MediumEnvironment Vars
MediumWildcard Dependency
LowScripts Present
LowWeak Cryptoplugins/platform-wecom_crypto/handler.js
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings