The Agent Skills Directory

[SAFE]: The skill acts as a wrapper for the bili CLI tool to perform standard operations on the Bilibili platform. All interactions and downloads target a well-known service.\n- [COMMAND_EXECUTION]: The skill executes the bili command-line utility to interact with the platform. This is the intended primary purpose of the skill.\n- [EXTERNAL_DOWNLOADS]: The skill fetches audio content and metadata from Bilibili's official servers. This is a core feature and targets a recognized service.\n- [PROMPT_INJECTION]: The skill processes user-generated content from Bilibili (subtitles, comments, and dynamics), which is an inherent attack surface for indirect prompt injection in tools that fetch web content.\n
Ingestion points: Video subtitles, comments, and dynamics fetched via bili video and bili feed (SKILL.md).\n
Boundary markers: None specified in the skill instructions.\n
Capability inventory: Shell command execution (bili) and file system access (writing audio files).\n
Sanitization: The skill does not perform explicit sanitization of fetched data before passing it to the agent context.

bilibili-cli