seedance-prompt

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly expects and directs the agent to ingest and interpret arbitrary user-provided images/videos/audio via @素材 references (see SKILL.md section 3.1 "素材角色指定" and README usage examples like "/seedance-prompt 我有3张图片..."), which are untrusted user-generated sources and could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:59 PM