skills/fengjiehzi/skills/1password/Gen Agent Trust Hub

1password

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the official 1Password command-line interface (op) to perform vault operations, secret injection, and authentication. These operations are essential to the skill's stated purpose of managing secrets.
  • [EXTERNAL_DOWNLOADS]: The skill defines an installation procedure using the Homebrew package manager (brew install 1password-cli) to fetch the official 1Password tool. This is a standard and safe method for software installation.
  • [DATA_EXFILTRATION]: While the skill reads sensitive secrets from vaults, it includes explicit guardrails (e.g., 'Never paste secrets into logs, chat, or code') to prevent unauthorized exposure. It recommends using op run and op inject to handle secrets in memory or through environment variables rather than writing them to disk.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from 1Password vaults and user-provided configuration files (e.g., .env, templates). The instructions emphasize using native CLI tools (op inject) which helps mitigate the risk of secrets being accidentally interpreted as instructions by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:45 AM