recommend-image

Warn

Audited by Snyk on Mar 12, 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 accepts and analyzes arbitrary GitHub URLs by delegating them to /detect-project (which uses GitHub MCP) as part of its required workflow, so untrusted, user-generated repository content can be ingested and influence image-selection decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 04:04 PM
Issues
1