alibabacloud-video-translation
Warn
Audited by Snyk on Apr 2, 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 fetches and ingests user/third-party media and subtitle files (OSS:// and https:// URLs) and requires the agent to "output subtitle content as-is" and use/examine extracted or external SRT content to choose languages and subsequent translation actions (see SKILL.md Scenario 2 / Phase 4 and references/api-parameters.md and workflow-details.md where InputConfig.Subtitle and CaptionExtraction flows are described), so untrusted, user-generated content can directly influence the agent's decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata