competition-dpapi-credential-chain

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires recording and preserving plaintext secrets, masterkeys, SIDs, and the “protected-artifact -> plaintext -> accepted-access” chain, which forces the agent to handle and potentially output secret values verbatim, creating exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). 该技能明确指导识别并解密 Windows DPAPI 主密钥和受保护 blob、恢复浏览器/保管库凭证并将明文重放以获得会话或特权——属于有意的凭证窃取与滥用，可用于未授权访问、横向移动和域级妥协。

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

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill explicitly guides recovering DPAPI-protected secrets and "replay" to obtain accepted access (active credential use and session creation), which encourages actions that can change or compromise the machine's state even if framed for a sandbox.