registry / @brutalist/mcp / 1.18.8

@brutalist/mcp@1.18.8

Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation continuation & intelligent pagination.

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.

Trigger

User or MCP client invokes a roast/debate operation with configured CLI agents or MCP servers.

Impact

A model-directed subprocess may act on the caller's workspace or access network tools; risk is capability exposure rather than a confirmed malicious chain.

Mechanism

Runtime orchestration of Claude, Codex, and Agy subprocesses plus optional Playwright installation.

Rationale

No concrete malicious behavior or unconsented lifecycle mutation is present. The package nevertheless exposes meaningful autonomous-agent and external-command capability that merits a warning for firewall users.

Evidence

package.jsondist/index.jsdist/cli-agents.jsdist/cli-adapters/claude-adapter.jsdist/cli-adapters/codex-adapter.jsdist/cli-adapters/agy-adapter.jsdist/mcp-registry.jsdist/transport/http-transport.js

Decision evidence

public snapshot

AI called this at 89.0% confidence with false-positive risk.

@brutalist/mcp@1.18.8

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code