evolink-image

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: 0.80). The skill explicitly accepts and uploads arbitrary public file URLs (see SKILL.md Step 2 "File Upload", references/api-params.md upload_file with file_url, and scripts/evolink-image-gen.sh --image examples) and then uses those untrusted, user-provided images as inputs that the agent will read/interpret for generation/editing, so third‑party content could materially influence tool behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 05:03 PM
Issues
1