cracking-passwords

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs embedding plaintext passwords, hashes, and hash-derived credentials into commands (e.g., -p 'Password123', -H 'hash', psexec.py -hashes :hash), which requires the LLM to handle and output secret values verbatim, creating exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content provides explicit, actionable instructions to steal credentials (hash extraction, Responder/mimikatz/secretsdump), perform credential stuffing/spraying and brute-force attacks, and use stolen hashes for pass‑the‑hash and remote code execution/lateral movement (psexec, wmiexec, crackmapexec), which are clearly malicious techniques enabling unauthorized system compromise.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Wordlist Generation and Useful Wordlists sections explicitly instruct scraping arbitrary public websites with tools like "cewl -w wordlist.txt https://example.com" and cloning public SecLists repos, which ingests untrusted third-party web content that is then used to generate wordlists and drive cracking actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs extracting and cracking local privileged credential stores (e.g., /etc/shadow, SAM hives), running privileged tools like mimikatz/secretsdump, and installing packages (apt install), which require sudo/privilege escalation and can compromise the host machine.