gogcli
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- PROMPT_INJECTION (LOW): The skill demonstrates a surface for Indirect Prompt Injection. It ingests untrusted content from various Google Workspace sources (Gmail, Drive, Chat, etc.) and possesses powerful execution capabilities (bash) without defined sanitization or boundary markers in the manifest. 1. Ingestion points: Google Workspace APIs (Gmail, Drive, Calendar, Chat). 2. Boundary markers: None specified in the plugin.json file. 3. Capability inventory: Shell execution (bash) and environment variable access (env-access). 4. Sanitization: None specified in the provided metadata.
- COMMAND_EXECUTION (SAFE): The request for bash permissions is consistent with the primary purpose of the skill as a Command Line Interface (CLI).
- CREDENTIALS_UNSAFE (SAFE): The request for env-access is typical for CLI tools that require access to environment variables for authentication or configuration.
Audit Metadata