registry / @marshell/cli / 0.7.1

@marshell/cli@0.7.1

Marshell CLI — join a subnet, discover agents, send messages

AI Security Review

scanned 9h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User runs marshell bridge run --auto-reply (or agent run) and receives a network message.

Impact

A malicious peer may prompt the locally installed agent to act in the selected workspace; optional hooks/webhooks extend this user-configured capability.

Mechanism

Remote-message-triggered Cursor/Hermes invocation with trusted workspace access.

Rationale

The package is not malicious by the install-time policy, but its explicit bridge mode creates an unresolved remote prompt-to-trusted-agent execution surface. Publish as a warning rather than block.

Evidence

package.jsonbin/marshell.jsdist/cli.jsdist/bridge.jsdist/config.jsdist/network.jsdist/pending.jsscripts/relay.mjs~/.marshell/config.json~/.marshell/pending/*.jsonworkspace supplied by --workspace or MARSHELL_WORKSPACE

Network endpoints1

network.marshell.dev

@marshell/cli@0.7.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code