cupp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill prompts for personal/secret target data (names, birthdates, etc.) and instructs generating wordlists that include those values verbatim, meaning the LLM would need to output sensitive values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly instructs how to generate targeted, personalized wordlists from OSINT and use them with tools like Hydra and Hashcat for brute-force/credential-guessing attacks, which is deliberate facilitation of credential theft and unauthorized access.