registry / agenthub-multiagent-mcp / 1.67.0
agenthub-multiagent-mcp@1.67.0
MCP server for AgentHub multi-agent communication
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged agent configuration behavior is scoped to temporary settings passed to worker-launched sessions. The reviewed storage, network, and dependency behavior aligns with the package’s AgentHub worker functionality, so the scanner hints do not establish an attack.
Static reason
No blocking static signals were detected.
Trigger
A user starts or configures the AgentHub worker; session capture is used for dispatched sessions.
Impact
The reviewed behavior enables the configured worker service and local session tracking; no malicious effect was established.
Mechanism
The worker authenticates to the configured AgentHub service, processes server messages, and launches Claude for dispatched work. Session capture uses a temporary settings file for that process rather than modifying global or project settings.
AI rationale
The manifest has no install lifecycle hook, and the flagged agent configuration behavior is scoped to temporary settings passed to worker-launched sessions. The reviewed storage, network, and dependency behavior aligns with the package’s AgentHub worker functionality, so the scanner hints do not establish an attack.
Network endpoints1
agenthub.contetial.com
Decision evidence
public snapshotAI called this Clean at 87.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes the package’s CLI entrypoints and has no preinstall, install, or postinstall hook.
- The worker connects to the configured AgentHub service with its API key and handles messages while running as a worker.
- Session capture is limited to worker-launched sessions and uses a temporary settings file; local journal and brain storage are under the Claude data directory.
- The inspected MCP, WebSocket, and Anthropic dependency files provide server transport and API client functionality.
- Skill-pack installation and shell setup are exposed as product commands, while the visualizer files generate local output.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNativeBindingsNetworkShellWebSocket
HighEntropyStringsUrlStrings
Source & flagged code
6 flaggeddist/commands/setup-shell.jsView file
25Trigger-reachable persistence chain: manifest.bin -> dist/setup.js -> dist/commands/setup-shell.js
L25: export function detectShell() {
L26: const shellPath = process.env.SHELL;
L27: if (!shellPath)
...
L35: export function rcFilePath(shell) {
L36: const home = os.homedir();
L37: return path.join(home, shell === "bash" ? ".bashrc" : ".zshrc");
L38: }
High
Trigger Reachable Persistence
A manifest entrypoint or package-local install chain reaches persistence behavior.
dist/commands/setup-shell.jsView on unpkg · L2525export function detectShell() {
L26: const shellPath = process.env.SHELL;
L27: if (!shellPath)
...
L35: export function rcFilePath(shell) {
L36: const home = os.homedir();
L37: return path.join(home, shell === "bash" ? ".bashrc" : ".zshrc");
L38: }
Medium
Install Persistence
Source writes installer persistence such as shell profile or service configuration.
dist/commands/setup-shell.jsView on unpkg · L25dist/worker.jsView file
Findings
3 High6 Medium4 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/worker.js
HighTrigger Reachable Persistencedist/commands/setup-shell.js
HighSemantic Analysis Limiteddist/brain/memvidBrain.js#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencedist/commands/setup-shell.js
MediumShips Native Binarynative/agenthub-memvid/agenthub-memvid.win32-x64-msvc.node
MediumShips Build Helperdist/run-claude.sh
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to agenthub-multiagent-mcp@1.67.0.
See all versions of agenthub-multiagent-mcp for other recorded verdicts.
- Review the evidence and your use of agenthub-multiagent-mcp@1.67.0 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.