Back to OT/ICS Threat Intelligence API
Card snapshot
ot-intel-api.onrender.com
·
2026-07-28 18:48:23 UTC
·
b8db401798f39cc635cb7a454e5831f01fb89a4b0e2301effea2f6d344a88a6c
This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.
{
"name": "OT/ICS Threat Intelligence API",
"description": "Hardware-aware threat intel for ICS/SCADA environments. Thirteen pay-per-call endpoints covering CVE triage, patch feasibility, internet-exposed device lookup, ICS threat actor profiles, sector threat mapping, IOC enrichment, live CISA advisory feed, asset risk verdict (escalate:true/false), active campaign tracker, sector change feed, ICS malware encyclopedia, complete sector threat brief with risk trend, and ASN infrastructure profiling for ICS threat actors. DeepSeek-enriched. No API keys \u2014 pure USDC micropayments on Base via x402.",
"url": "https://ot-intel-api.onrender.com",
"version": "1.0.0",
"documentationUrl": "https://ot-intel-api.onrender.com/SKILL.md",
"a2aEndpoint": "https://ot-intel-api.onrender.com/a2a",
"provider": {
"organization": "OT Intel API",
"url": "https://ot-intel-api.onrender.com"
},
"capabilities": {
"streaming": false,
"pushNotifications": false,
"stateTransitionHistory": false
},
"payment": {
"protocol": "x402",
"network": "eip155:8453",
"asset": "USDC",
"facilitator": "CDP (Coinbase Developer Platform)"
},
"skills": [
{
"id": "ot-cve-triage",
"name": "CVE Triage",
"description": "OT-contextualised CVE triage with OT-adjusted severity, CISA KEV status, and cyber-physical impact assessment.",
"tags": [
"cve",
"ics",
"scada",
"vulnerability",
"security"
],
"examples": [
"Triage CVE-2023-38802 for ICS impact",
"Is CVE-2021-34527 exploited in OT environments?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.02
},
{
"id": "ot-patch-feasibility",
"name": "Patch Feasibility",
"description": "AI-powered patch feasibility assessment for OT/ICS environments with downtime estimation and deployment strategy.",
"tags": [
"patch",
"ics",
"scada",
"vulnerability management"
],
"examples": [
"Can I patch CVE-2021-34527 without downtime?",
"Patch strategy for Siemens S7-1200"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.05
},
{
"id": "ot-device-exposure",
"name": "Device Exposure Lookup",
"description": "Internet-exposed OT device lookup by vendor/model with default credential risk and hardening recommendations.",
"tags": [
"device",
"ics",
"scada",
"exposure",
"shodan"
],
"examples": [
"Is Siemens S7-1200 exposed online?",
"Default credentials for Unitronics Vision"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.05
},
{
"id": "ot-threat-actor",
"name": "ICS Threat Actor Profiles",
"description": "ICS threat actor profiles with physical impact assessment, targeted sectors, and MITRE ATT&CK for ICS mapping.",
"tags": [
"threat actor",
"apt",
"ics",
"scada",
"mitre"
],
"examples": [
"Profile VOLTZITE threat actor",
"SANDWORM MITRE techniques"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.03
},
{
"id": "ot-actor-sector",
"name": "Sector Threat Actor Mapping",
"description": "All ICS threat actors targeting a specific industrial sector \u2014 energy, water, manufacturing, oil-and-gas, nuclear, chemical, transportation.",
"tags": [
"threat actor",
"sector",
"ics",
"energy",
"critical infrastructure"
],
"examples": [
"Which actors target energy sector?",
"ICS groups targeting water utilities"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.03
},
{
"id": "ot-ioc-enrichment",
"name": "IOC Enrichment",
"description": "IOC enrichment with ICS campaign context via AlienVault OTX \u2014 checks if indicator appears in OT-targeting threat feeds.",
"tags": [
"ioc",
"threat intel",
"ics",
"scada",
"otx"
],
"examples": [
"Is 185.220.101.45 associated with ICS attacks?",
"Enrich domain evil.com for OT context"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.01
},
{
"id": "ot-cisa-advisory",
"name": "CISA ICS Advisory Feed",
"description": "Live CISA ICS-CERT security advisories filtered by vendor or sector.",
"tags": [
"cisa",
"advisory",
"ics",
"scada",
"vulnerability"
],
"examples": [
"Latest CISA advisories for Siemens",
"Recent ICS advisories for energy sector"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.02
},
{
"id": "ot-exposure",
"name": "Asset Risk Verdict",
"description": "Asset-specific risk score and escalation verdict for OT/ICS devices. Returns risk_score (0-100), escalate (boolean), recommended_action, and contributing threat actors. Firmware-aware when firmware param provided.",
"tags": [
"risk-score",
"ics",
"scada",
"triage",
"escalation",
"asset-risk"
],
"examples": [
"What is the risk of internet-facing Siemens S7-1500 in energy sector?",
"Should I escalate this Schneider Modicon exposure?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.05
},
{
"id": "ot-campaign",
"name": "Active ICS Campaign Tracker",
"description": "Active campaigns targeting a specific industrial sector right now. Returns campaign name, actor, start date, targeted geography, TTPs in use, and CVEs being exploited.",
"tags": [
"campaign",
"ics",
"scada",
"active-threat",
"sector-monitoring"
],
"examples": [
"What campaigns are active in the electric sector?",
"Active ICS campaigns targeting water utilities"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.05
},
{
"id": "ot-delta",
"name": "Sector Change Feed",
"description": "What is NEW for a sector in the last N days \u2014 new CVEs, new CISA advisories, new actor activity. Designed for cron-based monitoring agents. Only returns changes, not the full picture.",
"tags": [
"delta",
"change-feed",
"ics",
"scada",
"monitoring",
"cron"
],
"examples": [
"What changed in water sector this week?",
"New ICS CVEs in energy sector last 7 days"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.03
},
{
"id": "ot-malware",
"name": "ICS Malware Encyclopedia",
"description": "Structured profiles of known ICS malware: PIPEDREAM, TRITON, INDUSTROYER2, CRASHOVERRIDE, FROSTYLOOP, BLACKENERGY. Returns capabilities, targeted protocols, attributed actor, and MITRE ATT&CK for ICS techniques.",
"tags": [
"malware",
"ics",
"scada",
"pipedream",
"triton",
"industroyer"
],
"examples": [
"Profile PIPEDREAM malware",
"What protocols does TRITON target?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.02
},
{
"id": "ot-brief",
"name": "Sector Threat Brief",
"description": "Complete 30-day threat brief for an industrial sector. Returns active actors, new CVE counts, active campaigns, top advisories, risk trend (increasing/stable/decreasing), and top 3 recommended actions. One call replaces 5+ chained calls.",
"tags": [
"brief",
"threat-brief",
"ics",
"scada",
"sector-report",
"risk-trend",
"compliance"
],
"examples": [
"Generate a 30-day threat brief for energy sector",
"What is the risk trend for water utilities?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.1
},
{
"id": "ot-asn-profiling",
"name": "ICS Threat Actor ASN Infrastructure Profiling",
"description": "Profiles an ASN for ICS threat actor infrastructure use. Returns actor associations (SANDWORM, VOLTZITE), phishing kit links, bulletproof hosting indicators, and OT-specific blocking recommendations. ASN analysis reveals infrastructure clustering that survives IP/domain rotation.",
"tags": [
"asn",
"infrastructure",
"ics",
"threat-actor",
"bulletproof-hosting",
"c2",
"blocking"
],
"examples": [
"Is AS215540 used by ICS threat actors?",
"Profile ASN AS9009 for OT infrastructure links",
"Should I block AS29802 at my OT firewall?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.03
},
{
"id": "ot-detection-artifacts",
"name": "ICS Detection Artifact Retrieval",
"description": "Returns YARA/Sigma detection rules for ICS malware families (PIPEDREAM, INDUSTROYER2, TRITON) and threat actors. Public corpus rules marked validated:true are safe for staging deployment. Synthesised rules carry validated:false. For automated threat hunting pipelines.",
"tags": [
"detection",
"yara",
"sigma",
"ics",
"threat-hunting",
"siem",
"pipedream",
"triton"
],
"examples": [
"Get YARA rules for PIPEDREAM",
"Sigma rules for SANDWORM TTPs",
"Detection artifacts for INDUSTROYER2"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.05
},
{
"id": "ot-compliance-mapping",
"name": "Multi-Framework Compliance Gap Mapping",
"description": "Returns triggered controls for a CVE or threat actor across 11 frameworks: NERC CIP, IEC 62443 (2-1/2-4/3-2/3-3/4-2), NIST 800-82, NIST CSF 2.0, CISA CPG, Saudi NCA OTCC, and UAE NESA IA. Deterministic mapping shows which controls apply, compliance status, required action, and compensating controls. Optional framework= param filters to one standard. For automated compliance reporting agents.",
"tags": [
"compliance",
"nerc-cip",
"iec-62443",
"nist-csf",
"nca-otcc",
"nesa-ia",
"ics",
"gap-analysis",
"audit",
"cve"
],
"examples": [
"What NERC CIP controls does CVE-2023-38802 trigger?",
"IEC 62443 gaps for SANDWORM activity",
"NCA OTCC posture for XENOTIME activity"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.04
},
{
"id": "ot-compliance-batch",
"name": "Aggregate Compliance Gap Assessment",
"description": "Rolls up compliance-gap mapping across multiple CVEs/threat actors in one call \u2014 deduplicated triggered controls, one aggregate severity rating (HIGH/MEDIUM/LOW/CLEAN), and a remediation summary. Same 11-framework coverage as ot-compliance-mapping. For agents triaging a batch of new advisories at once instead of one call per finding.",
"tags": [
"compliance",
"batch",
"nerc-cip",
"iec-62443",
"nist-csf",
"nca-otcc",
"nesa-ia",
"gap-analysis",
"audit"
],
"examples": [
"Batch-assess NESA gaps for these 5 CVEs from this week's advisories",
"Aggregate compliance severity for XENOTIME plus these 3 CVEs"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-threat-score",
"name": "Actor-Target Threat Score",
"description": "Deterministic capability x opportunity x intent threat score for an actor-target pairing. Scored from actor/CVE/campaign data plus live GDELT geopolitical tension and OFAC sanctions pressure signals. Not LLM-generated \u2014 the underlying score referenced by ot-risk-exposure and ot-action-conformance.",
"tags": [
"threat-score",
"risk-scoring",
"ics",
"capability",
"opportunity",
"intent",
"geopolitical",
"sanctions"
],
"examples": [
"What's SANDWORM's threat score against energy targets in Europe?",
"Score VOLTZITE's capability and intent against a Siemens/Schneider stack in GCC"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.04
},
{
"id": "ot-precursor-ttp",
"name": "Precursor / Dwell-Time TTP Breakdown",
"description": "Buckets an actor's known ATT&CK-for-ICS TTPs into pre-impact (reconnaissance through command-and-control \u2014 the early-warning window before physical/process disruption) vs impact-stage (inhibit-response-function, impair-process-control, impact). Deterministic tactic-taxonomy lookup \u2014 no LLM in the classification path.",
"tags": [
"ttp-analysis",
"dwell-time",
"early-warning",
"mitre-attck",
"ics",
"reconnaissance"
],
"examples": [
"How much of SANDWORM's activity is pre-impact vs impact-stage?",
"Does XENOTIME give an early-warning window before disruption?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.04
},
{
"id": "ot-root-cause-localization",
"name": "Statistical Anomaly Attribution",
"description": "Ranks which sensors most likely drove a reported OT/ICS anomaly by statistical deviation (z-score) from each sensor's own baseline, given a caller-supplied telemetry window. Fully deterministic, no LLM. A statistical approximation of the attribution goal in Oswal et al. 2025 (kernel SHAP + temporal convolution autoencoder) \u2014 not a trained model, no SHAP values computed.",
"tags": [
"anomaly-detection",
"root-cause",
"ics",
"scada",
"statistical",
"z-score"
],
"examples": [
"Which sensor caused this anomaly given these 5 tag histories?",
"Rank these 8 SCADA tags by deviation from baseline around the 14:32 event"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.15
},
{
"id": "ot-threat-hunt-control-loop",
"name": "Advisory Threat Hunt (Control-Loop Recon / RMM-LOTL)",
"description": "Flags control-loop reconnaissance patterns and living-off-the-land/RMM-tool abuse from caller-submitted process and command observations. Fully deterministic keyword-pattern matching, no LLM. Grounded in CyberAgentX and AgenticCyOps (arXiv 2603.09134) for the threat model, Dragos's control-loop mapping concept for the recon indicators. ADVISORY ONLY \u2014 never executes containment or any network action.",
"tags": [
"threat-hunting",
"advisory",
"rmm-abuse",
"living-off-the-land",
"ics",
"control-loop",
"keyword-matching"
],
"examples": [
"Flag any concerning patterns in these observed processes on an OT asset",
"Check this command history for living-off-the-land techniques"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.15
},
{
"id": "ot-invariant-reachability",
"name": "Physical Invariant Check",
"description": "Checks whether a tank/vessel's reported level change is physically consistent with its reported flow-in/flow-out over the same interval, via conservation of mass. Fully deterministic, no LLM. Loosely inspired by Barbhaya et al. 2025's physical-invariant residual check \u2014 not a reimplementation of their trained detection model. Flags inconsistency and direction; does not assert a specific cause.",
"tags": [
"physical-invariant",
"mass-balance",
"ics",
"scada",
"anomaly-detection",
"deterministic"
],
"examples": [
"Is this tank's level change consistent with its metered flows?",
"Check for a physical invariant violation on TANK_302 over the last minute"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-vendor-risk",
"name": "OT/ICS Third-Party Vendor Risk",
"description": "Supply-chain risk assessment for a specific OT/ICS vendor (e.g. Schneider Electric, Siemens, Rockwell Automation, ABB, Honeywell). Aggregates CVE, campaign, and threat actor mentions associated with the vendor and returns risk tier, confidence, and prescriptive supply-chain mitigation recommendations. Certain restricted-license third-party sources are excluded from analysis.",
"tags": [
"third-party-risk",
"supply-chain",
"ics",
"vendor-risk",
"vulnerability",
"cve"
],
"examples": [
"Assess supply-chain risk for Schneider Electric Modicon",
"What's the vendor risk for Siemens SIMATIC?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.15
},
{
"id": "ot-mitigation-map",
"name": "D3FEND-Mapped Mitigation Guidance",
"description": "Maps MITRE ATT&CK for ICS techniques to MITRE D3FEND defensive countermeasures for a given threat actor, CVE, or technique ID. The technique-to-D3FEND mapping is always deterministic (local crosswalk); DeepSeek only selects the relevant technique when actor/CVE is given, and writes prescriptive architecture recommendations.",
"tags": [
"architecture",
"d3fend",
"mitre-attck",
"ics",
"mitigation",
"defense-in-depth"
],
"examples": [
"What D3FEND controls mitigate SANDWORM's TTPs?",
"Mitigation guidance for T0836",
"Architecture recommendations for CVE-2024-XXXXX in a Schneider Modicon environment"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-risk-exposure",
"name": "Board/GRC Portfolio Risk Aggregator",
"description": "Aggregates deterministic threat-scores across the actors relevant to a sector+region, ranks them, and returns a DeepSeek-written board-level executive summary (BLUF, ICD-203 language). Optional compliance_framework param noted qualitatively in the narrative. For vCISO agents and GRC/board-reporting automation \u2014 portfolio-level companion to ot-threat-score.",
"tags": [
"grc",
"board-report",
"risk-exposure",
"executive-summary",
"ics",
"portfolio-risk"
],
"examples": [
"What's our risk exposure in the GCC energy sector?",
"Board summary of ICS threats to our water utility in KSA"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.4
},
{
"id": "ot-action-conformance",
"name": "Remediation Action Risk Gate",
"description": "Deterministic auto_approve/human_review/reject verdict for a planned remediation action (block_ip, quarantine_host, halt_pipeline, etc.) against an actor/sector/region context. Built on the same capability x opportunity x intent scoring as ot-threat-score, with auditable rules layered on top \u2014 no LLM in the decision path. For agents that need a governance checkpoint before executing high-impact actions.",
"tags": [
"governance",
"remediation",
"risk-gate",
"automation",
"ics",
"human-in-the-loop"
],
"examples": [
"Can I auto-block this IP linked to SANDWORM?",
"Should quarantining this host be human-reviewed first?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.12
},
{
"id": "ot-ai-exposure",
"name": "AI/Agentic Copilot Attack Surface Lookup",
"description": "Deterministic lookup of a vendor's publicly documented AI/agentic copilot in their OT/ICS product line, its autonomy level (advisory vs agentic \u2014 the primary risk differentiator), and the MITRE ATLAS techniques that apply given its access level. Hand-verified mapping, ATLAS IDs confirmed directly against the live matrix. No LLM in the lookup path.",
"tags": [
"ai-security",
"agentic-ai",
"mitre-atlas",
"copilot",
"ics",
"supply-chain"
],
"examples": [
"Does Siemens have an AI copilot, and what's its attack surface?",
"Is Honeywell's AI platform advisory or agentic?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-ai-uplift",
"name": "Attacker AI-Uplift Exposure",
"description": "Assesses how much a general-purpose AI agent (Claude, GPT) lowers the skill/time barrier for an attacker to find and reach a vendor's OT-adjacent footprint. Grounded in Dragos's May 2026 'AI in the Breach' precedent, not frontier-model governance thresholds. Distinct from ot-ai-exposure, which looks up a vendor's OWN embedded AI copilot. DeepSeek-synthesised over CTI corpus plus caller-declared deployment context.",
"tags": [
"ai-uplift",
"ai-security",
"reconnaissance",
"ics",
"supply-chain",
"it-ot-boundary"
],
"examples": [
"How much does AI lower the attack barrier for Schneider Electric's Modicon line?",
"Assess AI-uplift exposure for an internet-facing, single-factor-auth Siemens gateway"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-ai-attack-feasibility",
"name": "LLM-Generated ICS Attack Feasibility",
"description": "Deterministic lookup against one specific empirical study (Cook et al., ACM TOPS 2026) testing whether off-the-shelf LLMs (GPT-4o, Gemini, DeepSeek, Qwen, LLaMA \u2014 Claude excluded by the paper's own authors due to stronger safety guardrails) can generate working attack code against real PLCs. Narrow scope: only 3 vendors tested, only network/register-tags techniques ever succeeded, 1.08% overall success rate. Distinct from ot-ai-exposure (vendor's own AI copilot) and ot-ai-uplift (open-ended reconnaissance-uplift synthesis).",
"tags": [
"ai-security",
"llm-attack-synthesis",
"mitre-ics",
"empirical-study",
"ics",
"plc"
],
"examples": [
"Can an off-the-shelf LLM generate a working attack for Brute Force I/O?",
"Which techniques from the Triton campaign are LLM-achievable?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-claim-reliability",
"name": "CTI Claim Reliability Scoring",
"description": "Grounded in Meng et al., 'Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence' (arXiv:2509.23573v3, Feb 2026). Classifies a CTI claim against the paper's three failure modes \u2014 spurious correlation, contradictory knowledge, constrained generalization \u2014 using intel.db grounding plus DeepSeek synthesis. Returns a reliability score, verdict, corroborating/contradicting evidence, and confidence. Flags constrained_generalization and caps confidence at low whenever no grounding text is found, rather than letting the model claim corroboration it doesn't have.",
"tags": [
"cti-reliability",
"evidence-verification",
"empirical-study",
"ics",
"confidence-scoring"
],
"examples": [
"How reliable is the claim that SANDWORM has pivoted to Gulf water utilities?",
"Check this actor-attribution claim against intel.db before I act on it"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
},
{
"id": "ot-stix-coverage",
"name": "STIX Representability + Actionability Lookup",
"description": "Deterministic lookup grounded in Hahn, Krief, Rebori-Carretero, Puzis, Elyashar & Urlaub, 'An Evidence-Driven Analysis of Threat Information Sharing Challenges for Industrial Control Systems' (arXiv:2512.18714v3, Jan 2026). Returns whether STIX 2.1 can represent a technique/protocol/CVE's artifacts (full/partial/none) and whether public reporting gave enough technical detail to be actionable for detection engineering \u2014 answering what STIX sharing alone can't tell you. No LLM in the lookup path.",
"tags": [
"stix",
"threat-information-sharing",
"empirical-study",
"ics",
"detection-engineering"
],
"examples": [
"If SANDWORM shares T0836 activity via STIX, can I actually build a detection from it?",
"Does STIX have a way to represent Profibus command manipulation?"
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"price_usd": 0.2
}
]
}