AI Security Review
scanned 4d ago · by lpm-firewall-aiLPM blocks this version under the AI-agent control-surface policy. Install-time lifecycle mutates Claude/AI-agent control surfaces by installing skills and registering an MCP server. This gives the package a persistent agent tool/instruction foothold without a separate explicit user action beyond npm install.
Decision evidence
public snapshot- package.json defines postinstall: node scripts/postinstall.js
- scripts/postinstall.js copies package skills into ~/.claude/skills/{sidecar,second-opinion} during install
- scripts/postinstall.js registers MCP servers named amicus and sidecar in Claude Code/Desktop config
- MCP_CONFIG uses npx -y amicus@latest mcp, enabling future runtime code via agent tool config
- skills/sidecar/SKILL.md contains agent-operating instructions for launching amicus commands
- Postinstall actions are visible in README/package positioning for Claude sidecar integration
- No credential exfiltration endpoint found in inspected postinstall path
- Electron provisioning is cache-only by default unless AMICUS_PREFETCH_ELECTRON=1
- API key reads/writes are package-aligned setup/runtime behavior
Source & flagged code
5 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
bin/amicus.jsView on unpkg · L13Install-time source drops package-supplied AI-agent/MCP control files or instructions.
scripts/postinstall.jsView on unpkg · L5This package version adds a dangerous source file absent from the previous stored version.
src/sidecar/electron-install.jsView on unpkg