1password
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard package managers such as Homebrew and WinGet for installation, which are established and trusted methods for software distribution.
- [DATA_EXFILTRATION]: Secrets are managed through the official 1Password CLI and stored in a local environment file, following industry-standard practices for secret management without external exfiltration risks.
- [PROMPT_INJECTION]: The skill includes explicit guardrails advising the agent not to print raw secrets unless requested, which mitigates accidental data leakage. Additionally, it identifies the attack surface for indirect prompt injection via secret retrieval but maintains a safe posture through its intended primary use case.
Audit Metadata