bilibili-render-pdf
Warn
Audited by Snyk on May 25, 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). The skill explicitly requires the agent to fetch and ingest content from a public Bilibili URL (see "Source Acquisition" and "Subtitle Acquisition" with yt-dlp/whisper commands to download video, cover, subtitles and frames), which are untrusted/user-generated third-party sources and are read and acted on to drive segmentation, figure selection, and PDF generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata