bilibili-to-obsidian
Warn
Audited by Snyk on Mar 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly instructs fetching and extracting subtitles from public Bilibili URLs (e.g., "步骤 1：解析视频信息" and "video2text extract "<B站视频URL>"" / yt-dlp commands), so untrusted user-generated content from B站 is ingested and summarized and can materially influence subsequent outputs/actions.
Audit Metadata