compact-chat-history

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires verbatim quotes of user messages and detailed conversation/file content to be placed into the summary parameter sent to the tool, which would force the model to reproduce any API keys, tokens, or passwords present in the chat or referenced files.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill prompt is intentionally coercive and high-risk: it mandates aggregating verbatim user messages, file paths, and potentially sensitive data into a single tool-call (compact_chat_history) and forces immediate transmission, which creates a clear data-exfiltration vector and prompt-injection/backdoor-like behavior.