unocss-shadcn

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and consumes external MCP/registry content as part of its required workflow (see "Required MCP Chain" in SKILL.md: get_project_registries, search_items_in_registries, get_item_examples_from_registries and the lines "Use MCP outputs as the source of truth" / "Fetch example code from MCP"), meaning untrusted third‑party examples and metadata will be read and used to drive decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 09:48 AM