bilibili-render-pdf

Warn

Audited by Snyk on May 16, 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). This skill explicitly downloads and ingests content from public Bilibili URLs (see "Source Acquisition", "Subtitle Acquisition", and "Video and Cover Download" in SKILL.md) — including CC subtitles, Whisper transcripts, video frames, and the cover image — and requires the agent to read and interpret that untrusted, user-generated content to drive figure selection, segmentation, and the generated LaTeX/PDF output, so third-party content can materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 05:38 AM
Issues
1