classroom-setup

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the Python packages google-api-python-client, google-auth-oauthlib, and google-auth-httplib2. These are official, well-known libraries used for authenticating and interacting with Google APIs.
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage configuration directories and execute a local Python CLI script (classroom.py). These commands are used to automate the setup process and verify the connection to Google Classroom.
  • [DATA_EXPOSURE]: The skill handles sensitive OAuth credentials and authentication tokens stored in ~/.config/dgsw-classroom/. This local storage is a standard convention for CLI tools and there is no indication that these credentials are transmitted to any destination other than Google's authentication servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where user input (a file path) is interpolated into a shell command.
  • Ingestion points: The file path is obtained from the user via the AskUserQuestion tool.
  • Boundary markers: The path is placed directly into a cp command without specific delimiters or warnings to ignore embedded control characters.
  • Capability inventory: The skill has access to the Bash tool, allowing it to execute system commands.
  • Sanitization: No explicit sanitization or path validation is performed on the user-provided input before it is used in the command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 03:14 AM
Security Audit — agent-trust-hub — classroom-setup