spine-animation

Warn

Audited by Snyk on Mar 3, 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 pipeline (SKILL.md and scripts) explicitly sends user images to Google Gemini in split_character.py and ingests the generated atlas image from that third-party API (Gemini), which the agent then reads and uses to drive segmentation/positioning and downstream decisions, creating a pathway for indirectly injected content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 03:19 PM