secrets
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 1Password CLI (
op), GitHub CLI (gh), and Cloudflare'swrangler. These are official tools from well-known services used according to their design for secret management and deployment workflows. - [DATA_EXPOSURE]: The skill instructions involve reading local configuration files such as
~/.config/op/service-account-tokenand~/.config/op/environment-id. Accessing these files is a standard requirement for utilizing 1Password service accounts for automated secret retrieval. - [DATA_EXFILTRATION]: Provides functionality to register secrets with GitHub repositories using
gh secret set. This data movement targets a well-known service and is the primary intended purpose of the skill. - [PROMPT_INJECTION]: The skill processes untrusted inputs such as repository paths and secret names. It includes explicit instructions to mitigate risk by forbidding the output of secret values, lengths, or encoded representations to the console or logs. (Category: Indirect Prompt Injection).
Audit Metadata