ad-discovery

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to record and report discovered credentials (e.g., add_credential(..., secret="...") and "Current credentials" in return summaries) and shows numerous examples embedding plaintext passwords/tokens into commands, which requires the LLM to handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill is explicitly offensive: it contains multiple high-risk Active Directory attack and credential-theft techniques (credential harvesting from AD/SYSVOL/shares, ADCS/ADIDNS/relay/coercion guidance, DNS poisoning and instructions to capture credentials to an "attackbox", and commands to obtain tickets and machine credentials), which constitute deliberate malicious capability despite pentest framing.