trans

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local Python script (look_tongji.py) to manage the transcription workflow. The script is located within the repository's path structure.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with look.tongji.edu.cn to retrieve lecture data and slide snapshots. This domain is the official platform for Tongji University.
  • [INDIRECT_PROMPT_INJECTION]: By transcribing external video and audio content, the skill establishes an ingestion surface for untrusted data. The mandatory evidence chain includes ingestion points via the --lecture-url parameter and capability to write transcription artifacts to the local file system. Boundaries are maintained by the script processing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 11:56 AM
Security Audit — agent-trust-hub — trans