te-shared

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly documents a manual command ae-cli auth set-token <token> (and similar CLI usage) that instructs passing tokens as direct command-line arguments, which would require the LLM to include raw secret values verbatim in generated commands and thus poses an exfiltration risk.