abusing-shadow-credentials-for-privesc

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes commands embedding plaintext passwords and placeholders for secrets (e.g., -p "Passw0rd!", <PFX_PASSWORD>, , ) which require the LLM to handle or emit secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content explicitly documents and automates an Active Directory account takeover (Shadow Credentials) — including adding attacker keys, requesting PKINIT TGTs, extracting NT hashes, and reusing credentials — which is intentional malicious behavior enabling credential theft and privilege escalation.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly instructs modifying Active Directory objects (writing to msDS-KeyCredentialLink), generating attacker-controlled credentials, obtaining TGTs and NT hashes, and performing account takeover—i.e., state-changing malicious actions against target systems.