cred-spray

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read collected credentials (usernames, plaintext passwords, NTLM hashes) and embed them verbatim into commands and attack workflows (e.g., -p 'Password123!', -H 'HASH'), which requires the LLM to handle and output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). 该内容明确为恶意用途的操作手册：提供凭据喷洒（password/credential spray）、Pass‑the‑Hash、跨服务凭据复用、规避锁定检测及横向移动等逐步可执行命令与策略，明显用于未经授权的凭据滥用与扩大访问范围。