photokit

Warn

Audited by Snyk on Apr 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly loads and processes untrusted external content as part of its workflows — e.g., AsyncImage and the ImageLoader actor fetch arbitrary image URLs (references/image-loading-caching.md), AVPlayer/AVAsset examples play remote video URLs (references/av-playback.md), and PhotosPicker/Transferable flows ingest user-selected photos/videos (SKILL.md and references/photokit-patterns.md) — so third-party/user content is read and can influence runtime behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 22, 2026, 06:54 PM
Issues
1