cloning-project

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs the agent to extract project instructions and embed them verbatim into shell here-docs and to bundle user-uploaded files, so if those instructions or uploads contain API keys, tokens, or passwords the LLM would have to output them verbatim (exfiltration risk).