magicpath

Warn

Audited by Snyk on Mar 27, 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 reads user-provided content from the MagicPath platform (e.g., search/list-components/inspect return component source and previewImageUrl, and get-theme returns a designer "prompt" that the SKILL.md tells the agent to "Read the prompt field" and follow), which is untrusted third-party/user-generated content the agent is required to interpret and act on, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 05:23 PM
Issues
1