registry  /  osai-agent  /  4.2.63

osai-agent@4.2.63

OS AI Agent - YOUR AI AGENT

AI Security Review

scanned 4d ago · by lpm-firewall-ai

This is a user-invoked AI/sysadmin CLI with expected remote server, LLM, SSH, shell, and file-operation capabilities. The risky primitives are visible product functionality rather than hidden package attack behavior.

Static reason
One or more suspicious static signals were detected.
Trigger
User runs osai-agent commands such as run, connect, devices add, or provider configuration.
Impact
Can modify local files or run commands only during user-driven agent sessions; no confirmed malicious behavior.
Mechanism
interactive AI agent tool execution with confirmation gates and configured network services
Rationale
Static inspection shows a CLI AI agent with powerful but explicit user-invoked capabilities and no lifecycle hook, import-time payload, credential harvesting, or hidden exfiltration. The scanner secret finding is SSH private-key validation text in src/services/ssh.js, not an embedded secret.
Evidence
package.jsonsrc/index.jssrc/services/ssh.jssrc/services/server-url.jssrc/tools/local.jssrc/services/executor.jssrc/commands/devices.jssrc/safety/check.jssrc/agent/loop/tool-executor.jssrc/llm/direct.jsConf project storage for osai-agent~/.osai-agent/todos/*.json
Network endpoints12
wss://OLOJEDE-osai-agent-server.hf.spaceapi.anthropic.com/v1/modelsapi.anthropic.com/v1/messagesgenerativelanguage.googleapis.com/v1beta/modelsapi.openai.com/v1api.groq.com/openai/v1api.mistral.ai/v1api.deepseek.com/v1api.x.ai/v1api.cohere.ai/compatibility/v1api.perplexity.aiapi.together.ai/v1

Decision evidence

public snapshot
AI called this Clean at 86.0% confidence as Benign with medium false-positive risk.
Evidence for block
  • src/tools/local.js exposes shell and file-write/delete tools to the AI agent at user runtime.
  • src/commands/devices.js can upload encrypted device credentials to the configured server when user runs devices add.
Evidence against
  • package.json has no preinstall/postinstall/prepare lifecycle scripts.
  • src/index.js only dispatches explicit CLI commands; no hidden install-time execution found.
  • src/services/ssh.js validates user-supplied SSH keys and uses them only for ssh2 connections.
  • src/safety/check.js classifies write/dangerous commands and src/agent/loop/tool-executor.js prompts unless coding/noConfirm modes apply.
  • Network calls are package-aligned: auth/device/provider/agent server, LLM APIs, search providers, SSH/WebSocket features.
  • No credential harvesting, persistence, destructive startup behavior, or reviewer/prompt manipulation found.
Behavioral surface
Source
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShellWebSocket
Supply chain
HighEntropyStringsUrlStrings
Manifest
NoLicense
scanned 89 file(s), 712 KB of source, external domains: agent.osai.dev, api.anthropic.com, api.cerebras.ai, api.cohere.ai, api.deepinfra.com, api.deepseek.com, api.fireworks.ai, api.groq.com, api.hyperbolic.xyz, api.lingyiwanwu.com, api.mistral.ai, api.moonshot.ai, api.novita.ai, api.openai.com, api.perplexity.ai, api.siliconflow.cn, api.studio.nebius.ai, api.together.ai, api.x.ai, codestral.mistral.ai, dashscope.aliyuncs.com, generativelanguage.googleapis.com, html.duckduckgo.com, integrate.api.nvidia.com, models.github.ai, ollama.com, open.bigmodel.cn, openrouter.ai, osaix.vercel.app, qianfan.baidubce.com, router.huggingface.co

Source & flagged code

6 flagged · loading source
src/services/ssh.jsView file
19patternName = private_key_openssh severity = critical line = 19 matchedText = /^-----B...--/,
Critical
Critical Secret

Package contains a critical-looking secret pattern.

src/services/ssh.jsView on unpkg · L19
19patternName = private_key_openssh severity = critical line = 19 matchedText = /^-----B...--/,
Critical
Secret Pattern

OpenSSH private key in src/services/ssh.js

src/services/ssh.jsView on unpkg · L19
20patternName = private_key_rsa severity = critical line = 20 matchedText = /^-----B...--/,
Critical
Secret Pattern

RSA private key in src/services/ssh.js

src/services/ssh.jsView on unpkg · L20
22patternName = private_key_ec severity = critical line = 22 matchedText = /^-----B...--/,
Critical
Secret Pattern

EC private key in src/services/ssh.js

src/services/ssh.jsView on unpkg · L22
src/ui/components/ConfirmationDialog.jsView file
41patternName = generic_password severity = medium line = 41 matchedText = h(Text, ...')),
Medium
Secret Pattern

Hardcoded password in src/ui/components/ConfirmationDialog.js

src/ui/components/ConfirmationDialog.jsView on unpkg · L41
src/agent/loop/tool-executor.jsView file
243patternName = generic_password severity = medium line = 243 matchedText = this.rea...)));
Medium
Secret Pattern

Hardcoded password in src/agent/loop/tool-executor.js

src/agent/loop/tool-executor.jsView on unpkg · L243

Findings

4 Critical4 Medium5 Low
CriticalCritical Secretsrc/services/ssh.js
CriticalSecret Patternsrc/services/ssh.js
CriticalSecret Patternsrc/services/ssh.js
CriticalSecret Patternsrc/services/ssh.js
MediumNetwork
MediumEnvironment Vars
MediumSecret Patternsrc/ui/components/ConfirmationDialog.js
MediumSecret Patternsrc/agent/loop/tool-executor.js
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowNo License