agentscope-ai / agentscope-ai/agentscope
[Feature]: Sandbox mechanism during skill runtime
Aperta
- Lingua principale
- Python
- Stelle
- 31.5k
- Fork
- 3.5k
- Merge medio
- 1g 23h
- PR unite (30g)
- 95
Descrizione
In agentScope, regarding the runtime of skills and the use of capabilities such as execute_shell_command, execute_python_code, and view_text_file, should a unified sandbox be provided to restrict the dynamic nature of these LLM calls?
Guida per i contributori
Apri la guida per i contributori
Valutazione
Questa issue non è ancora stata valutata.