registry / @robota-sdk/agent-command / 3.0.0-beta.77

@robota-sdk/agent-command@3.0.0-beta.77

Consolidated command module implementations for Robota SDK CLI

AI Security Review

scanned 10h 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.

Trigger

A user invokes /plugin, /reload-plugins, or /shell.

Impact

A user-selected marketplace/plugin or shell command can execute with that user's permissions.

Mechanism

User-directed plugin lifecycle and terminal command execution.

Rationale

This is not malware or an install-time hijack, but it exposes a real user-invoked AI-agent extension lifecycle and command-execution capability. Warn under the firewall policy for explicit agent configuration/extension mutation.

Evidence

package.jsonsrc/plugin/plugin-command.tssrc/plugins/default-plugin-command-adapter.tssrc/plugins/default-plugin-command-source-loader.tssrc/shell/shell-command.tssrc/shell/shell-command-module.ts~/.robota/plugins~/.robota/settings.json.robota/plugins

Decision evidence

public snapshot

AI called this at 88.0% confidence with false-positive risk.

@robota-sdk/agent-command@3.0.0-beta.77

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code