paper-collage-ad

Fail

Audited by Snyk on Aug 8, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). The repository invokes a remote shell installer (astral.sh) and clones/runs third‑party ML runtimes from an external GitHub user (solar2ain) and calls an unusual Ark API host (ark.cn-beijing.volces.com) — these are unvetted remote install/source locations that can deliver executables or be typosquat endpoints, so they raise significant risk.

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

  • Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can reach the LLM at runtime through ChatCut’s Gemini Omni prompt construction in the optional Phase 3.5 workflow (Gemini Omni motion draft/localized edit), where the agent supplies prompt/continueFrom/refImages and the prompt content can incorporate user-approved or user-provided story/script text.

Issues (2)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 8, 2026, 02:37 PM
Issues
2
Security Audit — snyk — paper-collage-ad