holoviz-mcp-cli

Warn

Audited by Snyk on Mar 1, 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 includes "Search the web as a last resort" and an "inspect " command (e.g., "holoviz-mcp inspect http://... / inspect specific URL") in SKILL.md, showing it can fetch and return arbitrary public web pages/results (in Markdown/JSON) that an agent would read and could therefore influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:15 AM