eli5-compress

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill mandates copying inline code and fenced code blocks exactly (and overwriting files), which forces the LLM to reproduce any secrets/API keys present verbatim—effectively a copy/paste exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The tool deliberately sends entire file contents (including originals and full backups) to an external "claude" CLI for compression (and again when fixing), creating a clear data-exfiltration vector and persistent plaintext backups that can leak secrets or sensitive environment values.