Overview
Details
Dataset sources, attribution, and notes about how pages are built.
About PromptRiskDB
PromptRiskDB builds AI security pages from public records. The site connects MITRE ATLAS techniques, mitigations, case studies, MIT AI Risk Repository records, MITRE ATT&CK context, CISA KEV entries, and selected NVD CVE enrichment.
Every page is generated from imported records and saved relationships. The exporter may add headings, summaries, navigation, and source links, but it does not invent incident facts, vulnerability details, or dataset claims.
How pages are built
Pages are built from cleaned local copies of public records and saved connections between them. The page builder adds structure, headings, and labels, but does not create new incident facts or vulnerability claims outside the imported datasets.
Sources and attribution
Original source
CISA Known Exploited Vulnerabilities
CISA KEV marks CVEs that are known to have been exploited and adds vendor, product, remediation, and ransomware context.
Original source
MIT AI Risk Repository
The MIT AI Risk Repository provides AI risk records, domain taxonomy, causal taxonomy, and publication metadata.
Original source
MITRE ATLAS Data
ATLAS provides the AI security tactics, techniques, mitigations, and case studies used as the central map for these pages.
Original source
MITRE ATT&CK Enterprise STIX
MITRE ATT&CK Enterprise provides the broader cybersecurity technique, tactic, mitigation, and STIX context linked from ATLAS records.
Original source
NVD CVE API 2.0
NVD enriches selected CVEs with severity, status, references, weakness, and vulnerability detail fields.