persona-it-admin
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data including "pending IT requests" and "audit logs". If these sources contain malicious instructions, the agent might be influenced to perform unauthorized administrative actions.
- Ingestion points: Processes IT requests and audit logs through the
gwsworkflow and monitoring instructions. - Boundary markers: No explicit delimiters or instructions are provided to ensure the agent ignores embedded commands within the processed data.
- Capability inventory: The skill relies on the
gwsbinary, which provides administrative capabilities for Google Workspace (Gmail, Drive, Calendar). - Sanitization: No sanitization or validation of the input data is specified in the instructions.
- [COMMAND_EXECUTION]: The skill utilizes a custom command-line interface
gwsto perform IT administration tasks. This binary is required for the skill to function as intended.
Audit Metadata