Incidents (JSON)
Incidents with their grade, reasons, models, enrichment and sources.
289 incidents · 654 KBThe whole ledger as files you can download, with a guide to every field.
The whole ledger is free to download. It is current to 17 Nov 2026 and holds 289 incidents. It is a list of published reports and it will have gaps and errors; the about page says what it can and cannot tell you.
Incidents with their grade, reasons, models, enrichment and sources.
289 incidents · 654 KBEvery registered source with its kind, role and sweep date.
271 sources · 44 KBOne row per incident, for a spreadsheet. List fields are joined with semicolons.
289 incidents · 222 KBOne row per registered source, with the number of incidents that cite it.
271 sources · 23 KBThe same data, with its history, in the public Substrate repository.
The fields in incidents.json, with the values a closed field can take. The sources file has two closed fields of its own: role (swept, cited, unreachable); kind (model-provider, vendor-ti, government, court-record, incident-database, academic, press, regional-cert). Source rows also carry swept (the sweep date) and, for sources we could not read, public_note.
idtitledatedisclosedactivityactoractor_typecriminal, nation-state, hacktivist, unknownnexustargetsai_rolerecon, vuln-research, exploit-dev, malware-dev, malware-runtime-llm, phishing-content, social-engineering, deepfake, ops-automation, agentic-intrusion, data-analysis, evasion, fraud, supply-chain, llmjacking, agent-hijackmodelsmodel_basisstated-by-vendor, stated-by-researcher, stated-by-victim, inferred, unknownautonomyassist, semi-autonomous, autonomousoutcomeconfidenceCONFIRMED, STRONG, SUSPECTEDconfidence_reasonsummaryquotesingle_source_reasonsourcessources[].titlesources[].publishersources[].urlsources[].datesources[].kindsources[].verified_onsources[].quote_foundsources[].archive_urlsources[].fetch_statussources[].primarysources[].primary_via_partysources[].aggregator_onlyenrichmentenrichment.modelsopenness: closed, open-weight, criminal, unknown, kind: llm, coding-agent, deepfake-video, voice-clone, image, harness, otherenrichment.model_namedtrue, falseenrichment.harnesskind: open-source, commercial-agent, custom, noneenrichment.countriesenrichment.country_basisattributed, language-or-infrastructure, noneenrichment.sectorsfinance, crypto, government, defense, technology, ai-platforms, software-supply-chain, telecom, healthcare, education, critical-infrastructure, energy, manufacturing, retail, media, legal, individuals, enterprise-broad, unknownThe data is published under the license of the Substrate repository: MIT License, Copyright (c) 2025 Daniel Miessler. Short quotes from sources are credited to their publishers and remain under the publishers' terms. If you use the data, please cite it as hackingincidents.ai, Unsupervised Learning, accessed <date>.