together-images
Warn
Audited by Snyk on Mar 4, 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's SKILL.md and references/api-reference.md (and scripts/generate_image.py) explicitly show image editing using an image_url that fetches arbitrary public URLs (e.g., https://cdn.pixabay.com/...), so the agent ingests untrusted third‑party images as part of its core workflow which could contain instructions or content that materially influence generation behavior.
Audit Metadata