1password
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides examples of shell commands utilizing the 1Password CLI (
op) to read, create, and edit vault items. It demonstrates how to securely pipe these values into other CLI tools likedocker,gh, andtogglwithout exposing secrets in the shell history. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests content from external secret fields.
- Ingestion points: The output from the
op readcommand is brought into the agent's execution context for use in variables and subsequent commands. - Boundary markers: No explicit boundary markers or instructions to ignore embedded content within the secret values are provided in the examples.
- Capability inventory: The skill allows for command execution and interaction with third-party CLI tools (SKILL.md).
- Sanitization: The skill assumes the integrity of the 1Password vault content and does not suggest specific validation or sanitization of the retrieved secret strings before use.
Audit Metadata