The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes external command-line tools including yt-dlp for downloading video and metadata and whisper for transcribing audio content (SKILL.md).
[DYNAMIC_EXECUTION]: The skill generates LaTeX source code and compiles it into final PDF documents. It also supports the execution of Python scripts to generate teaching visualizations using libraries like matplotlib and seaborn (SKILL.md).
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as Bilibili video metadata, subtitles, and transcripts which may contain malicious instructions designed to influence the agent's behavior or output. 1. Ingestion points: Bilibili video metadata, CC subtitles, and Whisper-transcribed audio are ingested into the agent context via SKILL.md. 2. Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore instructions embedded within the processed content. 3. Capability inventory: The agent can execute shell commands (yt-dlp, whisper), compile LaTeX, and run Python scripts for image generation. 4. Sanitization: No explicit sanitization or filtering of external content is described.

bilibili-render-pdf