cors-misconfiguration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires the agent's return summary to list "New credentials or tokens found" (and shows examples embedding cookie/session values in commands), which would force the LLM to handle and potentially output secret values verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Highly suspicious — the list contains many attacker-controlled/“evil” domains, typosquat and malformed origins, JSONP/script endpoints and exfiltration paths, plus internal/localhost targets that together are typical indicators of malicious hosting, origin-reflection CORS abuse and potential malware/credential exfiltration channels.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is an explicit offensive guide that instructs and provides ready-to-run PoCs for stealing authenticated responses, session data, and internal information via CORS misconfigurations and subdomain takeover — deliberate data exfiltration and credential theft for attackers.