registry / fullcourtdefense / 1.7.27

fullcourtdefense@1.7.27

Full Court Defense — real-time AI firewall and CLI scanner for chatbots, agents and RAG pipelines. Tool-call guards for MCP, LangChain, LlamaIndex, AutoGen, CrewAI and Semantic Kernel.

AI Security Review

scanned 4h ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. Explicit CLI setup can install broad AI-agent hooks/gateways and persistent discovery schedules. `install-all` defaults to desktop-posture upload and daily scheduling.

Static reason

No blocking static signals were detected.

Trigger

User runs `fullcourtdefense install-all`, `auto-protect`, `discover --schedule`, or an install-* command.

Impact

Can persistently intercept agent actions and transmit discovered workstation posture to the vendor service.

Mechanism

CLI-managed agent configuration, telemetry upload, and recurring task creation.

Rationale

No automatic npm-install execution or concrete malicious chain was found. The package nevertheless has broad, persistent agent-extension and inventory-upload capabilities activated by explicit setup commands.

Evidence

package.jsondist/cli/commands/installAll.jsdist/cli/commands/autoProtect.jsdist/cli/commands/discover.jsdist/cli/commands/discoverSchedule.jsdist/cli/commands/mcpGateway.js~/.cursor/hooks.json~/.claude/settings.json~/.codex/config.toml~/.fullcourtdefense-spool.jsonlcrontab~/Library/LaunchAgents/ai.fullcourtdefense.discover.plist

Network endpoints1

fullcourtdefense@1.7.27

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code