registry / agenthub-multiagent-mcp / 1.71.0
agenthub-multiagent-mcp@1.71.0
MCP server for AgentHub multi-agent communication
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe flagged shell persistence and agent configuration writes are tied to explicit setup commands, while the worker sends its API key to the configured AgentHub server for its stated coordination function. I found no malicious credential flow, install-time action, or unrelated account activity.
Static reason
No blocking static signals were detected.
Trigger
The worker connects when launched; shell and skill setup changes require their corresponding explicit setup commands.
Impact
Expected AgentHub communication and user-requested setup changes; no unauthorized collection or unrelated account action was found.
Mechanism
The worker authenticates to the configured AgentHub server. Setup commands can add a shell hook or install the package’s skills into the user’s Claude configuration.
AI rationale
The flagged shell persistence and agent configuration writes are tied to explicit setup commands, while the worker sends its API key to the configured AgentHub server for its stated coordination function. I found no malicious credential flow, install-time action, or unrelated account activity.
Evidence
~/.agenthub/worker.json~/.bashrc~/.zshrc~/.agenthub/shell-init.shOS temporary directory: agenthub-worker-* files
Network endpoints2
agenthub.contetial.comConfigured AGENTHUB_URL
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest describes an AgentHub MCP server and exposes named commands for the server, worker, daemon, and setup.
- The worker uses its configured AgentHub server URL and API key to authenticate its WebSocket connection.
- Shell profile changes are performed by the explicit `install-shell` setup subcommand.
- Skill installation is dispatched only when the setup command receives `--skills`; its installer writes skill files as part of that operation.
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@1.71.0.
See all versions of agenthub-multiagent-mcp for other recorded verdicts.
- Review the evidence and your use of agenthub-multiagent-mcp@1.71.0 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.