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

1password

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the 1Password CLI ('op') using the Homebrew package manager ('brew'), an established and well-known service.
  • [COMMAND_EXECUTION]: Executes the 'op' and 'tmux' binaries to manage secret retrieval and authentication. It dynamically constructs commands to interact with tmux sessions and sockets.
  • [DATA_EXFILTRATION]: The skill provides the capability to read sensitive secrets, such as database passwords and private SSH keys, and can write them to the local file system using the '--out-file' flag or the 'op inject' command.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where the agent processes potentially untrusted data from 1Password vaults or local template files.
  • Ingestion points: Secret attributes from 1Password vaults and template files (e.g., 'config.yml.tpl') used during the 'op inject' workflow.
  • Boundary markers: No explicit markers or instructions are provided to the agent to ignore potentially malicious instructions embedded in vault data or templates.
  • Capability inventory: Significant capabilities including 'op' CLI for secret management and 'tmux' for command execution, with the ability to create or modify local files.
  • Sanitization: No sanitization or validation of the content retrieved from the vault or the provided templates is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:10 AM
Security Audit — agent-trust-hub — 1password