registry / biel-search / 0.1.80

biel-search@0.1.80

Ask AI chatbot for technical documentation

AI Security Review

scanned 23h 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 opens Connect and selects Copilot or Cursor.

Impact

Can add a remote MCP endpoint to the selected AI coding tool.

Mechanism

User-invoked MCP configuration via IDE deep link.

Rationale

The package is not malicious by source evidence, but it provides an explicit user-triggered capability to install a remote MCP server into AI coding tools. Per policy this warrants a warning rather than a block.

Evidence

package.jsondist/collection/services/biel-service.jsdist/collection/services/biel-websocket-service.jsdist/collection/components/biel-input-options/biel-input-options.js

Network endpoints3

app.biel.ai/api/v1wss://app.biel.ai/ws/messagesmcp.biel.ai/v2

Decision evidence

public snapshot

biel-search@0.1.80

AI Security Review

Decision evidence

Source & flagged code

Findings