bilibili-to-obsidian

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs well-known third-party utilities yt-dlp and ffmpeg, and the author's vendor package @wangjs-jacky/video2text for processing video and text data.
  • [COMMAND_EXECUTION]: Utilizes system commands to fetch video metadata, extract subtitles, and manage directory structures within the user's local Obsidian vault.
  • [PROMPT_INJECTION]: Subject to indirect prompt injection risks due to processing external content.
  • Ingestion points: Metadata and subtitles extracted from Bilibili videos, which originate from untrusted third-party sources.
  • Boundary markers: Lacks explicit delimiters or instructions to ignore embedded commands when the agent processes the extracted text for summarization.
  • Capability inventory: Can execute command-line tools and perform write operations on the local file system.
  • Sanitization: Does not implement validation or filtering for the extracted video content before use in subsequent tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:54 PM