tools-1password-cli

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides extensive documentation for the 1Password op CLI, allowing the agent to perform vault operations, read/write secrets, and manage service accounts. This is the primary function of the skill and involves executing shell commands to interact with the 1Password binary.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads data from external sources (1Password vaults). If a vault item, such as a Secure Note or a field description, contains malicious instructions, the agent might interpret those as commands when retrieving the secret content. This is a inherent risk factor for any tool that processes external or shared data.
  • [EXTERNAL_DOWNLOADS]: The documentation references installation methods via npx and curl from the vendor's GitHub repository and npm. These are standard distribution channels for the skill author and well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:04 AM