bilibili-search-download
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing internal Python scripts (
scripts/bilibili_search.pyandscripts/bilibili_download.py) which handle interaction with the Bilibili data services. These scripts are invoked with arguments passed from the user's natural language requests.\n- [EXTERNAL_DOWNLOADS]: The utility makes network requests to the RedFox API atredfox.hkto perform keyword searches and resolve video download URLs. These operations are essential to the skill's primary function and target the vendor's own infrastructure.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata from external sources (Bilibili video titles and descriptions), which represents a potential attack surface for indirect prompt injection. \n - Ingestion points: Video metadata fetched via
bilibili_search.pyand displayed to the user.\n - Boundary markers: None explicitly defined to separate data from instructions.\n
- Capability inventory: The skill uses Python scripts to fetch and return data to the agent for display; it does not execute the data content.\n
- Sanitization: The skill instructions suggest removing special characters like
|and newlines for formatting purposes.
Audit Metadata