registry / @fnclaude/cli / 2.14.0

@fnclaude/cli@2.14.0

fnclaude CLI implementation (TypeScript rewrite, in progress)

AI Security Review

scanned 3h 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

User runs fnc; renderer behavior additionally requires FNC_RENDERER.

Impact

A Claude session can request project switching, session spawning, clipboard writes, and injected slash commands; configured launchers may start processes.

Mechanism

Claude MCP control tools and optional permission bypass

Rationale

The package is not concretely malicious, but it exposes high-impact AI-agent controls and an opt-in permission-bypass mode. Treat as a warning for dangerous capability rather than a block.

Evidence

package.jsonsrc/main.tssrc/mcp/inject-config.tssrc/mcp/handlers/spawn.tssrc/launch/renderer-mount.tssrc/mcp/dispatch.tssrc/handoff/spawn-launcher.ts

Decision evidence

public snapshot

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

@fnclaude/cli@2.14.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code