registry / @agentvault/openai-bridge / 0.1.7
@agentvault/openai-bridge@0.1.7
AgentVault OpenAI Codex bridge for encrypted owner messages and rooms
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe inspected source supports ordinary bridge behavior: explicit local login, constrained Codex execution, and replies delivered through AgentVault. The scanner's command-output finding is not supported by this path, which disables shell access and sends the model reply to the addressed conversation.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user invokes the CLI; a model turn starts when the bridge handles an owner message or addressed room message.
Impact
No unauthorized credential transfer, command-output collection, or malicious persistence was established.
Mechanism
The child uses a dedicated home directory and read-only workspace, with shell, web, and integration tools disabled; the resulting reply is sent through AgentVault.
AI rationale
The inspected source supports ordinary bridge behavior: explicit local login, constrained Codex execution, and replies delivered through AgentVault. The scanner's command-output finding is not supported by this path, which disables shell access and sends the model reply to the addressed conversation.
Network endpoints1
api.agentvault.chat
Decision evidence
public snapshotAI called this Clean at 96.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package manifest lists a prepublish-only build hook and the ws runtime dependency.
- The CLI uses the AgentVault API origin and requires HTTPS; Codex login is a separate interactive command.
- Codex runs with a dedicated home directory and a read-only workspace.
- A turn handles an owner message or addressed room message, disables filesystem, shell, web, and integration tools, then delivers the reply through the bridge.
- The ws dependency exposes its normal Node and browser entrypoints, has no install lifecycle hook, and the flagged operation sets a WebSocket protocol header.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShellWebSocket
HighEntropyStringsUrlStrings
Source & flagged code
9 flaggeddist/index.jsView file
103286await init_bridge();
L103287: import { spawn as spawn2 } from "node:child_process";
L103288: import { realpathSync } from "node:fs";
...
L103298: checkBinary: checkVersion,
L103299: output: (text) => process.stdout.write(text + "\n"),
L103300: command: (binary, args2, options = {}) => new Promise((resolve4, reject) => {
L103301: const child = spawn2(binary, args2, { env: options.env ?? { PATH: "/usr/bin:/bin", HOME: process.env.HOME, XDG_RUNTIME_DIR: process.env.XDG_RUNTIME_DIR, DBUS_SESSION_BUS_ADDRESS: p...
Critical
Command Output Exfiltration
Source executes local commands and sends command output to an external endpoint.
dist/index.jsView on unpkg · L103286103286Trigger-reachable chain: manifest.main -> dist/index.js
L103286: await init_bridge();
L103287: import { spawn as spawn2 } from "node:child_process";
L103288: import { realpathSync } from "node:fs";
...
L103298: checkBinary: checkVersion,
L103299: output: (text) => process.stdout.write(text + "\n"),
L103300: command: (binary, args2, options = {}) => new Promise((resolve4, reject) => {
L103301: const child = spawn2(binary, args2, { env: options.env ?? { PATH: "/usr/bin:/bin", HOME: process.env.HOME, XDG_RUNTIME_DIR: process.env.XDG_RUNTIME_DIR, DBUS_SESSION_BUS_ADDRESS: p...
Critical
Trigger Reachable Dangerous Capability
A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior.
dist/index.jsView on unpkg · L103286Findings
2 Critical6 High5 Medium5 Low
CriticalCommand Output Exfiltrationdist/index.js
CriticalTrigger Reachable Dangerous Capabilitydist/index.js
HighChild Processdist/index.js
HighShell
HighSame File Env Network Executiondist/index.js
HighCredential Redirect Persistencedist/index.js
HighTrigger Reachable Command Output Exfiltrationdist/index.js
HighSemantic Analysis Limiteddist/index.js
MediumNetwork
MediumEnvironment Vars
MediumOversized Source Filedist/index.js
MediumOversized Cli Entrypointdist/index.js
MediumStructural Risk Force Deep Review
Affected versions and remediation
This report applies to @agentvault/openai-bridge@0.1.7.
See all versions of @agentvault/openai-bridge for other recorded verdicts.
- Review the evidence and your use of @agentvault/openai-bridge@0.1.7 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.