hmos-appfreeze-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). Insecure because the prompt mandates including "original log" fragments verbatim (and running extraction scripts), so if those logs contain API keys, tokens, cookies, or passwords the LLM would be required to output them, creating an exfiltration risk.