iblai-agent-mcp

Warn

Audited by Snyk on May 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's Add MCP Connector dialog and MCP Servers REST API explicitly accept arbitrary "Connector Server" URLs and register external MCP servers (via POST mcp-servers/) which the agent can connect to and stream from (SSE/WebSocket/HTTP), so it clearly ingests untrusted, third-party content at runtime that can influence tool behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 01:38 PM
Issues
1