agentscope-developer

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the AgentScope framework from its official GitHub repository and install it via standard package managers like pip and uv.- [COMMAND_EXECUTION]: Implementation examples are provided for using tools that execute shell commands and Python code, which are native features of the AgentScope toolkit.- [PROMPT_INJECTION]: The skill outlines an architecture where agents ingest user input via a UserAgent interaction loop. While the documentation includes a directive for input validation, the provided code templates do not implement specific boundary markers or sanitization logic for the execute_shell_command and execute_python_code capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:56 AM