secrets
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
op run,gh secret set, andwranglerto manage environment variables and repository secrets. - [DATA_EXFILTRATION]: The skill facilitates the transfer of secrets from 1Password environments to external GitHub repositories using the GitHub CLI (
gh). - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface by reading local configuration files and using their contents in shell commands.
- Ingestion points: Sensitive local files
~/.config/op/service-account-tokenand~/.config/op/environment-id. - Boundary markers: Includes specific prohibitions against echoing or outputting secret values to the terminal, logs, or chat.
- Capability inventory: Can execute shell commands via multiple CLI tools including
op,gh, andwrangler. - Sanitization: No programmatic sanitization or validation of the configuration file contents is described beyond the agent following the provided instructions.
Audit Metadata