Missing User Warnings
Medium
- Confidence
- 89% confidence
- Finding
- The skill explicitly instructs the agent to collect and pass third-party API keys on the command line, but it does not warn that these secrets are highly sensitive or constrain how the agent should handle them. In agent environments, secrets entered into commands may be exposed through logs, shell history, transcripts, process listings, or accidental echoing back to the user, which creates a realistic credential-leak risk.
