registry / @omniforge/mission-control / 0.7.2

@omniforge/mission-control@0.7.2

Mission Control is a local-first control panel for running AI coding agents against your own repositories. It turns a request into a scoped ticket, routes that ticket through a workflow, keeps local project memory, and can hand completed work to PR or MR

AI Security Review

scanned 2d ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. The runtime can configure extensions for Claude, Cursor, Kiro, and Codex in a selected project when launching agent work. No unconsented install-time agent-control mutation or data-exfiltration path was found.

Static reason

One or more suspicious static signals were detected.

Trigger

Explicit Mission Control runtime agent launch with configured extensions

Impact

Can enable or disable configured agent extensions for the chosen project.

Mechanism

writes project-local agent extension configuration and CLI overrides

Rationale

No concrete malicious behavior was found, but the package deliberately controls AI-agent extension configuration within selected projects. Per policy, this first-party agent extension lifecycle risk warrants a warning rather than a block.

Evidence

package.jsonscripts/ensure-node-pty.mjsbin/mc.jsdist/server.jsdist/chunk-RVG2ZUKC.js.claude/settings.local.json.cursor/mission-control-extensions.json.kiro/hooks/mission-control-extensions.json

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence as Dangerous Capability with false-positive risk.

@omniforge/mission-control@0.7.2

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code