image-upscaling

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's documentation and workflow explicitly accept arbitrary image_urls in SKILL.md (remote public URLs) and the SSE event reference (references/SSE-EVENTS.md) shows web_search_query/web_search_citations flows, indicating the agent fetches and ingests open web content which can influence processing and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:57 AM