registry / agenthub-multiagent-mcp / 1.65.0
agenthub-multiagent-mcp@1.65.0
MCP server for AgentHub multi-agent communication
AI Security Review
scanned 17d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the reviewed agent configuration and persistence behavior is tied to runtime product features or explicit setup. The source inspected did not establish a concrete attack surface.
Static reason
No blocking static signals were detected.
Trigger
Running the MCP server or invoking the relevant setup command.
Impact
No confirmed harmful effect or unconsented control-surface abuse was established.
Mechanism
Runtime features write agent activity or memory locally; capture-hook setup checks consent, and shell setup adds a managed shell block when requested.
AI rationale
The manifest has no install lifecycle hook, and the reviewed agent configuration and persistence behavior is tied to runtime product features or explicit setup. The source inspected did not establish a concrete attack surface.
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes explicit command entrypoints and has no install lifecycle hook.
- The auto-activity hook is disabled by an environment setting and writes only to Claude settings when enabled; its runtime is intended to record coarse local activity.
- Brain journal and memory paths store agent data under the local Claude brains directory; test paths use temporary homes.
- Capture-hook setup checks server consent before applying settings, and the worker excerpt shows logging and connection setup.
- Shell profile changes are performed by the explicit shell-install command.
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@1.65.0.
See all versions of agenthub-multiagent-mcp for other recorded verdicts.
- Review the evidence and your use of agenthub-multiagent-mcp@1.65.0 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.