Deterministic remediation risk gate. Pass actor, sector, region, planned_action (e.g. block_ip, halt_pipeline, disable_account). Returns auto_approve/human_review/reject via capability x opportunity x intent scoring (same as /ot/threat-score) — no LLM in the loop. auto_approve requires vendor_stack; omitting it caps the verdict at human_review regardless of score. Optional asset_context escalates to human_review on shared cloud/CDN infra (e.g. shared_infra:cloudflare).

ICS threat actor profile. Pass ?name=SANDWORM. Returns MITRE ATT&CK ICS techniques, known malware, attribution, physical impact, targeted sectors, and OT detection recommendations. Alias lookup supported: Volt Typhoon→VOLTZITE, APT44→SANDWORM. Covers all Dragos Activity Groups.

ICS threat actors by sector. Pass ?sector=energy. Returns all groups targeting that sector from live MITRE ATT&CK ICS STIX data. Covers energy, water, manufacturing, oil-and-gas, chemical, transportation, nuclear.

Live CISA ICS-CERT advisories filtered by vendor or sector. Pass ?vendor=siemens or ?sector=energy. Returns advisory IDs, CVSS scores, CVE lists, OT severity, and sector tags. Up to 25 results.

Deterministic lookup against Cook et al. (ACM TOPS 2026) testing whether off-the-shelf LLMs generate working ICS attack code. Pass technique (name/ID, e.g. 'Brute Force I/O' or T0806), vendor (Siemens, Schneider Electric, Rockwell Automation — only these tested), and/or campaign (Industroyer2, Fuxnet, FrostyGoop, INCONTROLLER, Stuxnet, Triton). Only Network/Register-Tags techniques succeeded; 1.08% success rate; Claude excluded (stronger guardrails). No LLM in lookup path.

AI/agentic copilot exposure lookup for OT/ICS vendors. Pass vendor (Siemens, Schneider Electric, Rockwell Automation, ABB, Emerson, Honeywell, Yokogawa, GE Vernova, Omron, Mitsubishi Electric). Returns the vendor's documented AI/agentic copilot, autonomy level (advisory vs agentic — the key risk differentiator), access, and applicable MITRE ATLAS techniques. Hand-verified mapping, ATLAS IDs confirmed against the live atlas.mitre.org matrix. Deterministic, no LLM in the lookup path.

Assesses how much a general-purpose AI agent (not a specialized ICS tool) lowers the barrier for an attacker to reach a vendor's OT-adjacent footprint. Grounded in Dragos's May 2026 water-utility precedent, not governance thresholds. Distinct from /ot/ai-exposure (vendor's own AI copilot). Input: vendor (required); product, internet_facing, auth_type, segmented (all optional; unknown caps tier at informational). DeepSeek-synthesized, ICD-203 language.

Publication-ready CTI article ~700 words. Pass ?actor=CHERNOVITE or ?cve=CVE-XXXX-XXXX. Fans out to actor/cve + campaign + malware + advisory. DeepSeek writes journalist-style: headline, lede, body with ATT&CK context, defanged IOCs, analyst assessment, TLP. Ready for threat intel blog or advisory publication.

ICS threat actor ASN infrastructure profiling. Pass ?asn=AS215540. Returns ICS actor associations (SANDWORM, VOLTZITE, XENOTIME), phishing kit links (Tycoon2FA, EvilProxy, NakedPages), bulletproof hosting indicators, abuse categories (c2, staging, phishing), and an OT-specific blocking recommendation with WAF rule hint. ASN analysis reveals infrastructure clustering that survives IP/domain rotation — critical for OT defenders tracking persistent actor infrastructure.

Sector threat brief for ICS/OT. Pass ?sector=energy&period=30. Returns active actors, new CVE counts, active campaigns, top advisories, and risk_trend (increasing/stable/decreasing). One call replaces 5+ chained calls. Ideal for weekly reporting and compliance dashboards.

Active ICS campaign tracker. Pass ?sector=electric&status=active. Returns campaigns currently targeting a sector with actor attribution, start date, targeted geography, TTPs in use, and CVEs being exploited. No free equivalent for live campaign status.

CTI claim reliability scoring, grounded in Meng et al. (arXiv:2509.23573, Feb 2026). Pass claim=<text>, optionally actor= and/or cve_id= to ground against intel.db. Classifies the claim against three failure modes — spurious correlation, contradictory knowledge, constrained generalization — and returns a reliability score, verdict, and evidence. The confidence layer threat-score/dossier/report don't expose.

Compliance gap mapping for a CVE or threat actor across 11 frameworks: NERC CIP, IEC 62443, NIST 800-82, NIST CSF 2.0, CISA CPG, Saudi NCA OTCC, UAE NESA IA. Pass ?cve_id=CVE-2023-38802 or ?actor=SANDWORM, optionally &framework=<value> to filter. Returns triggered controls (e.g. CIP-007-6 R2, IEC 62443-3-3 SR 5.1), status (NON_COMPLIANT_IF_UNMITIGATED / REVIEW_REQUIRED), required action, and compensating controls. For automated compliance reporting agents on cron.

OT-contextualised CVE triage for ICS/SCADA. Pass ?id=CVE-XXXX-XXXX. Returns OT-adjusted severity, cyber-physical impact, patch feasibility, CISA KEV status, and prioritised action. DeepSeek-enriched with live NVD and CISA-KEV data.

ICS sector change feed — only what is NEW in the last N days. Pass ?sector=water&days=7. Returns new CVEs, new CISA advisories, and new actor activity since the last call. Designed for cron-based monitoring agents. Eliminates redundant reprocessing.

ICS detection artifact retrieval. Pass ?target=PIPEDREAM or ?target=SANDWORM&format=sigma. Returns YARA/Sigma rules for the target malware or actor, sourced from public corpus (Florian Roth signature-base, CISA advisories) with validated:true, or DeepSeek-synthesised with validated:false. Designed for automated threat hunting pipelines that commit rules to SIEMs and EDRs — validated:true rules are safe to deploy; validated:false require lab testing first.

ICS/OT device exposure lookup. Pass ?vendor=siemens&model=s7-1200. Returns default credential risk, exposed OT protocols (Modbus/502, S7comm/102, DNP3/20000), exploitation notes, and hardening steps. Covers Siemens, Schneider, Rockwell, Honeywell, GE, Unitronics, Beckhoff.

Deep actor intelligence dossier. Pass ?actor=SANDWORM. Fans out to actor, campaign, malware, ioc, asn, detection primitives and synthesises via DeepSeek. Returns full profile, infrastructure, IOC table, detection rules, kill chain mapping. Most comprehensive single-call artifact available.

OT asset risk verdict. Pass ?vendor=siemens&model=s7-1500&sector=energy&network=internet-facing. Returns risk_score (0-100), risk_level, escalate (boolean), recommended_action, active CVEs, and threat actors. Optional firmware param enables firmware-specific CVE matching. Cached 1 hour.

IOC enrichment with ICS campaign context. Pass ?value=1.2.3.4&type=ip or type=domain. Queries AlienVault OTX, AbuseIPDB, and DeepSeek CTI for OT campaign association. Returns verdict on whether the IOC is linked to ICS-targeting campaigns.

LinkedIn post for CTI/ICS security audience. Pass ?actor=VOLTZITE or ?cve=CVE-XXXX-XXXX. Fans out to actor or cve + advisory. Returns hook line, 3-5 intelligence bullets, call to action, hashtags. Ready to publish. Ideal for security practitioners and threat intelligence teams sharing findings.

ICS malware encyclopedia. Pass ?name=PIPEDREAM. Returns capabilities, targeted OT protocols, attributed actor, affected vendors, detection signatures, and MITRE ATT&CK ICS techniques. Covers PIPEDREAM, TRITON, INDUSTROYER2, CRASHOVERRIDE, FROSTYLOOP, BLACKENERGY.

Prescriptive D3FEND-mapped mitigation guidance for OT/ICS threats. Pass one of ?actor=<threat actor name>, ?cve_id=<CVE ID>, or ?technique_id=<MITRE ATT&CK ICS technique ID e.g. T0836>, optionally with &vendor_stack=<vendor/product context e.g. Schneider Modicon>. Returns matched ATT&CK ICS techniques mapped to D3FEND defensive countermeasures with priority and rationale, plus prescriptive architecture recommendations. DeepSeek-synthesised, ICD-203 estimative language.

OT/ICS patch feasibility for a CVE. Pass ?id=CVE-XXXX-XXXX. Returns patch availability, OT-safe workarounds, patch complexity per ICS layer, estimated downtime, safe-to-patch-live flag, deployment strategy, and risk-vs-disruption score 1-10.

Synthesised Markdown threat actor report for ICS/OT. Pass ?actor=CHERNOVITE&sector=energy. Fans out to actor, campaign, malware, advisory, detection primitives internally (no extra charge) and synthesises via DeepSeek. Returns executive summary, TTPs, campaigns, malware, recommended actions. TLP: WHITE.

Board/GRC-level portfolio risk aggregator. Pass sector and region. Aggregates the same deterministic capability x opportunity x intent scoring used by /ot/threat-score across the actors relevant to that sector, ranks them, and returns a DeepSeek-written executive summary (BLUF structure, ICD-203 language). Optional compliance_framework noted qualitatively in the narrative. Portfolio-level companion to /ot/threat-score — for vCISO agents and GRC/board-reporting automation.

Sector situation report. Pass ?sector=energy&period=30. Fans out to actor/sector, advisory, campaign, delta, compliance primitives. Returns 30-day threat landscape, top actors, new advisories, what changed, compliance posture, recommended priorities. Designed for weekly security briefing automation.

Capability x opportunity x intent threat score for an actor-target pairing. Pass actor, sector, region, vendor_stack. Deterministic scoring: actor/CVE/campaign data plus GDELT tension and OFAC sanctions pressure. Not LLM-generated.

OT/ICS supply-chain vendor risk assessment. Pass ?vendor=(name) e.g. Schneider Electric, Siemens, Rockwell Automation, optionally &product=(line) e.g. Modicon. Returns risk tier, confidence, cited CVEs (KEV/EPSS), threat actors with historical targeting interest, and supply-chain mitigation recommendations. DeepSeek-synthesised, ICD-203 language. Certain restricted-license sources excluded.

X/Twitter thread (5-7 posts) for an ICS actor or CVE. Pass ?actor=XENOTIME or ?cve=CVE-XXXX-XXXX. Fans out to actor or cve. Returns thread array: hook post, intel posts with ATT&CK IDs and affected OT systems, mitigation post, hashtag post. Each post under 280 characters.