clawcut

Warn

Audited by Snyk on Jun 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The Gradio runtime ingests outsider-authored free text from the userโ€™s โ€œ๐Ÿ“ Topic / Themeโ€ textbox and passes it into generate_video_pipeline() โ†’ generate_script_gemini() as contents.append(f"Topic: {topic}"), which is then sent to Gemini as LLM-readable text (indirect prompt-injection risk via user-supplied topic).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 29, 2026, 10:49 AM
Issues
1