Recon

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains explicit, actionable offensive guidance (exploit chains, RCE/webshell upload, NTDS.dit/Mimikatz credential theft, lateral movement and persistence), automated scanning/attack orchestration, and a mandatory silent notification step — all of which present a high dual‑use/abuse risk if misused.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill ingests outsider-authored free text via public web content fetched at runtime (e.g., PassiveRecon/DomainRecon call crt.sh and ipinfo.io and parse their JSON/text responses into the LLM prompt context).