securing-systems

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content contains multiple explicit, actionable offensive techniques (C2 examples, reverse shells/shellcode, credential theft via Mimikatz/Pass-the-Hash, persistence mechanisms, DNS/domain exfiltration examples, obfuscation/exec patterns and supply-chain attack guidance) that are dual-use but clearly enable unauthorized compromise and data exfiltration if used outside authorized contexts.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflows and code explicitly instruct querying open third‑party OSINT and reputation services (e.g., threat-intel.md's "IOC automatic query" / IOCChecker.check_hash that calls https://www.virustotal.com/api/v3/files/{file_hash}, plus subfinder/amass/Shodan/AbuseIPDB references), so the agent is expected to fetch and interpret untrusted public content which can influence decisions like IOC triage and response.