ot-ics-attack

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This is an explicit offensive OT/ICS attack playbook with step‑by‑step exploit code and tactics (Modbus/DNP3/S7/EtherNet‑IP/OPC UA/BACnet/FINS) that instructs reading/extracting firmware and credentials, writing registers, stopping PLCs, injecting false telemetry, manipulating certificates, hooking engineering tools and hiding malicious OB blocks — clearly enabling deliberate malicious actions with potential physical harm.

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 1 workflow in SKILL.md explicitly instructs using public search engines like Shodan/Censys (e.g., "shodan search ...") and pulling data from public sites/GitHub, which the agent would ingest and interpret to choose targets and subsequent actions, exposing it to untrusted third‑party content that can materially influence behavior.