1password
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes system commands including
tmuxand the 1PasswordopCLI to manage authentication and secret retrieval. - [EXTERNAL_DOWNLOADS]: Fetches and installs the official 1Password CLI package using the Homebrew package manager.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted data retrieved from 1Password vaults. 1. Ingestion points: Secret content retrieved via
op readorop injectand session output captured viatmux capture-pane(SKILL.md). 2. Boundary markers: None identified; vault content is not isolated using delimiters or safety instructions. 3. Capability inventory: Includes command execution (op,tmux,date), environment variable modification (export), and file system operations (mkdir). 4. Sanitization: No evidence of sanitization or validation of data retrieved from the vault is present before it is used by the agent.
Audit Metadata