ck-help

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires executing a script with user-provided arguments and mandates showing the script's COMPLETE output verbatim (after translating/passing "$ARGUMENTS"), which would force the LLM to echo any secrets or API keys present in arguments or script output, creating high exfiltration risk.