1password

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): The skill explicitly promotes the use of curl -sSL ... | bash to install dependencies and the skill itself from canifi.com. This is an untrusted source that enables immediate, arbitrary command execution on the user's system.
  • [EXTERNAL_DOWNLOADS] (HIGH): Downloads are sourced from canifi.com, which does not belong to the list of Trusted External Sources. This significantly increases the risk of supply chain attacks or malicious payload delivery.
  • [CREDENTIALS_UNSAFE] (HIGH): The skill is designed to handle extremely sensitive data, including OP_SERVICE_ACCOUNT_TOKEN, SERVICE_EMAIL, and SERVICE_PASSWORD. Because the installation method is insecure (RCE), these credentials are at high risk of being intercepted or exfiltrated by the installation scripts.
  • [COMMAND_EXECUTION] (MEDIUM): The setup process relies on a custom, unverified CLI utility canifi-env. Executing unverified binaries or scripts to manage environment variables can lead to persistent system compromise or privilege escalation.
Recommendations
  • HIGH: Downloads and executes remote code from: https://canifi.com/install.sh, https://canifi.com/skills/1password/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 05:40 PM
Security Audit — agent-trust-hub — 1password