together-images
Warn
Audited by Snyk on Mar 31, 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 explicitly accepts and fetches arbitrary public URLs for image inputs and LoRA adapters (see references/api-reference.md "reference_images" and "image_loras", scripts/kontext_editing.py using image_url and download_image, and lora_generation.py pointing to HuggingFace/CivitAI/Replicate URLs), so untrusted third‑party content is ingested and can materially influence generation behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata