bilibili-downloader

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists only of a documentation file (SKILL.md). The actual implementation script mentioned (scripts/bili_dl.cjs) is missing from the provided files, preventing a full behavioral analysis of the execution logic.
  • [COMMAND_EXECUTION] (SAFE): The documentation defines a command-line interface for downloading videos. While the tool is designed to execute a local script, no evidence of dangerous command injection or shell escapes was found in the documentation.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses an attack surface for indirect prompt injection as it processes external URLs.
  • Ingestion points: video_url argument.
  • Boundary markers: None specified in the documentation.
  • Capability inventory: Likely involves network requests and file-system writes (per the description).
  • Sanitization: Verification of URL/BV number format is mentioned as an error check, which provides a basic layer of input validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM