one-password

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes examples that embed secret values verbatim (e.g., export OP_SERVICE_ACCOUNT_TOKEN="eyJhbGci...", credential="sk-...") and shows commands and code that retrieve and place secrets directly into environment variables or variables, which would require an agent to handle or output secret values verbatim.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The prompt explicitly instructs modifying the user's SSH configuration (~/.ssh/config) to use a 1Password IdentityAgent socket and directs installing the 1Password CLI—actions that change system configuration and affect authentication state, so it should be flagged even though it doesn't request sudo or new user creation.