nebula

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly exposes AI assistants to arbitrary user-generated memories via Nebula APIs and MCP tools (e.g., references/mcp-setup.md's search_memories and references/rest-api.md POST /v1/memories/search and the SDK search methods), which return content from trynebula.ai that the agent is expected to read and could materially influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The Claude Desktop MCP config includes the command "npx -y mcp-remote https://mcp.trynebula.ai/mcp …", which will fetch and execute the remote npm package "mcp-remote" at runtime while connecting to https://mcp.trynebula.ai/mcp, so remote code is executed as part of the skill's runtime setup.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 06:05 AM