bilibili-downloader

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the bilibili-api-python package from PyPI, which is the primary dependency for accessing Bilibili content.
  • [PROMPT_INJECTION]: The skill processes untrusted metadata from Bilibili, creating an indirect prompt injection surface where video titles or subtitles could influence file system operations.
  • Ingestion points: Metadata is retrieved via API calls in scripts like download_video.py and download_subtitles.py.
  • Boundary markers: No explicit markers are used to delimit external content or instruct the agent to ignore instructions embedded in metadata.
  • Capability inventory: The skill possesses file-writing and directory-creation capabilities across all provided Python scripts.
  • Sanitization: Basic sanitization is performed on video titles by replacing slashes with underscores, which mitigates simple directory traversal attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 03:01 AM