registry  /  amicus  /  1.7.7

amicus@1.7.7

Multi-model LLM Council + parallel AI window for Claude Code. Run structured council reviews across Gemini, GPT, DeepSeek and more — or fork a conversation to any model and fold the results back.

AI Security Review

scanned 1d ago · by lpm-firewall-ai

Install-time script mutates Claude/AI-agent control surfaces by installing package-supplied skills and registering MCP servers. This gives the package persistent invocation paths in future AI-agent sessions without an explicit runtime command from the user.

Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
npm install runs postinstall
Impact
Future Claude/AI-agent sessions may load package instructions and invoke amicus MCP/CLI tools, including spawning model sidecars with inherited environment and workspace context.
Mechanism
unconsented lifecycle AI-agent skill and MCP registration
Attack narrative
On installation, the lifecycle script copies package-authored Claude skills into the user's global Claude skills directory and registers amicus/sidecar MCP entries for Claude Code and Claude Desktop. Those entries run npx -y amicus@latest mcp, creating a persistent AI-agent integration path beyond normal package import or CLI use.
Rationale
The confirmed issue is not generic network or credential handling; it is install-time mutation of Claude skills and MCP configuration, an AI-agent control surface. Under the firewall boundary, unconsented lifecycle registration of agent instructions/tools is blocking behavior even if the package's stated purpose is AI sidecars. Product guard normalized a concrete AI-agent control hijack publish_block to the blockable dangerous-capability shape.
Evidence
package.jsonscripts/postinstall.jsskills/sidecar/SKILL.mdskills/second-opinion/SKILL.mdsrc/mcp-server.jssrc/utils/env-loader.jssrc/utils/auth-json.js~/.claude/skills/sidecar/SKILL.md~/.claude/skills/second-opinion/SKILL.md~/.claude/skills/second-opinion/COUNCIL-DESIGN.md~/.claude/skills/second-opinion/MODEL-NOTES.md~/.claude.json~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%/Claude/claude_desktop_config.json~/.config/claude/claude_desktop_config.json

Decision evidence

public snapshot
AI called this Malicious at 96.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for block
  • package.json defines postinstall: node scripts/postinstall.js.
  • scripts/postinstall.js copies package skills into ~/.claude/skills/sidecar and ~/.claude/skills/second-opinion.
  • scripts/postinstall.js registers MCP servers in Claude Code/Desktop configs, including fallback writes to ~/.claude.json and claude_desktop_config.json.
  • MCP config uses command npx with args ['-y','amicus@latest','mcp'], causing future agent sessions to invoke this package.
  • skills/sidecar/SKILL.md contains agent-triggering instructions to spawn amicus commands and use Build mode with full tool access.
Evidence against
  • Postinstall is visible in package.json, best-effort, and can be skipped with AMICUS_SKIP_POSTINSTALL=1.
  • Network/API code appears aligned with an LLM sidecar tool rather than credential exfiltration.
  • Credential loader reads known provider keys into process.env for model access and does not show outbound exfiltration by itself.
  • MCP server constrains explicit project roots before spawning sidecar sessions.
Behavioral surface
Source
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetwork
Supply chain
HighEntropyStringsUrlStrings
ManifestNo manifest risk signals triggered.
scanned 124 file(s), 760 KB of source, external domains: aistudio.google.com, api.anthropic.com, api.deepseek.com, api.openai.com, console.anthropic.com, generativelanguage.googleapis.com, nodejs.org, openrouter.ai, platform.deepseek.com, platform.openai.com, www.w3.org

Source & flagged code

5 flagged · loading source
package.jsonView file
scripts.postinstall = node scripts/postinstall.js
High
Install Time Lifecycle Scripts

Package defines install-time lifecycle scripts.

package.jsonView on unpkg
scripts.postinstall = node scripts/postinstall.js
Medium
Ambiguous Install Lifecycle Script

Install-time lifecycle script is not statically allowlisted and needs review.

package.jsonView on unpkg
bin/amicus.jsView file
13try { L14: const { migrateLegacyConfigDir } = require('../src/utils/config'); L15: const _m = migrateLegacyConfigDir();
Medium
Dynamic Require

Package source references dynamic require/import behavior.

bin/amicus.jsView on unpkg · L13
scripts/postinstall.jsView file
5Install-time AI-agent control hijack evidence: L5: * L6: * 1. Copies SKILL.md to ~/.claude/skills/sidecar/ L7: * 2. Registers MCP server in Claude Code (~/.claude.json) L8: * 3. Registers MCP server in Claude Desktop/Cowork config ... L36: function skillsRoot() { L37: return path.join(os.homedir(), '.claude', 'skills'); L38: } ... L58: L59: if (!existing.mcpServers) { existing.mcpServers = {}; } L60: L61: const prev = existing.mcpServers[name]; L62: const status = !prev ? 'added' : JSON.stringify(prev) !== JSON.stringify(config) ? 'updated' : 'unchanged'; Payload evidence from skills/sidecar/SKILL.md: L11: run_in_background: true. Never run amicus start/resume/continue in the foreground. L12: (2) The fold summary returns on stdout when the user clicks Fold in the GUI or the L13: headless agent finishes. Use TaskOutput to read it when the background task completes. ... L69: **Step 1: Get an OpenRouter API key** L70: - Sign up at https://openrouter.ai L71: - Go to Keys → Create Key ... L78: mkdir -p ~/.local/share/opencode L79: cat > ~/.local/share/opencode/auth.json << 'EOF' L80: { ... L119: L120: Add these to your shell profile (`~/.bashrc`, `~/.zshrc`) for persistence. L121:
Critical
Ai Agent Control Hijack

Install-time source drops package-supplied AI-agent/MCP control files or instructions.

scripts/postinstall.jsView on unpkg · L5
src/mcp-server.jsView file
matchType = previous_version_dangerous_delta matchedPackage = amicus@1.8.1 matchedIdentity = npm:YW1pY3Vz:1.8.1 similarity = 0.858 summary = stored previous version shares package body but lacks this dangerous source file
High
Previous Version Dangerous Delta

This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.

src/mcp-server.jsView on unpkg

Findings

1 Critical2 High5 Medium4 Low
CriticalAi Agent Control Hijackscripts/postinstall.js
HighInstall Time Lifecycle Scriptspackage.json
HighPrevious Version Dangerous Deltasrc/mcp-server.js
MediumAmbiguous Install Lifecycle Scriptpackage.json
MediumDynamic Requirebin/amicus.js
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings