Law / Frameworks / Crosswalk / OWASP LLM Top 10 to NIST CSF 2.0

The OWASP Top 10 for LLM Applications, mapped to the NIST Cybersecurity Framework

5 of OWASP LLM Top 10's controls connect to 2 of NIST CSF 2.0's through 10 laws in 4 jurisdictions. Two controls connect when the same duties, in at least 2 laws we track, reach both. The connections are our own reading of the law; no framework publisher has reviewed or endorsed them.

From
OWASP Top 10 for LLM Applications, 2026 edition, August 2026, OWASP GenAI Security Project
To
NIST Cybersecurity Framework, version 2.0, February 2024 (NIST CSWP 29), National Institute of Standards and Technology
See also
NIST CSF 2.0 to OWASP LLM Top 10, the other way · every pair in the crosswalk · law library as of

Download this mapping, with every law behind each connection: owasp-llm-top-10--nist-csf.csv · owasp-llm-top-10--nist-csf.json

OWASP LLM Top 10NIST CSF 2.0LawsJurisdictionsWhere the laws stand
LLM01:2026Prompt Injection PR.IR-03Mechanisms are implemented to achieve resilience requirements in normal and adverse situations 2 1 1 in force, 1 not yet in force
The 2 laws behind LLM01:2026 and PR.IR-03
LLM02:2026Sensitive Information Disclosure PR.IR-03Mechanisms are implemented to achieve resilience requirements in normal and adverse situations 2 1 1 in force, 1 not yet in force
The 2 laws behind LLM02:2026 and PR.IR-03
LLM03:2026Excessive Agency PR.PS-04Log records are generated and made available for continuous monitoring 8 4 4 in force, 4 not yet in force
The 8 laws behind LLM03:2026 and PR.PS-04
LLM04:2026Supply Chain PR.IR-03Mechanisms are implemented to achieve resilience requirements in normal and adverse situations 2 1 1 in force, 1 not yet in force
The 2 laws behind LLM04:2026 and PR.IR-03
LLM05:2026Data and Model Poisoning PR.IR-03Mechanisms are implemented to achieve resilience requirements in normal and adverse situations 2 1 1 in force, 1 not yet in force
The 2 laws behind LLM05:2026 and PR.IR-03
Not connected to the NIST CSF 2.0: 5 of OWASP LLM Top 10's controls

No law we track reaches these

No duty in the laws we track reaches these controls.

Lines of the scraping and news aggregation laws we track were not read against the NIST CSF 2.0, so none of them connects the two here (how each subject's lines were read).

How these connections are drawn

Each requirement line in the laws we track is read against the framework for its subject (the AI, scraping and news aggregation laws against the NIST AI RMF, the privacy, communications and age assurance laws against the NIST Privacy Framework, the cybersecurity laws against the NIST CSF 2.0); laws on liability and content moderation are not read against any framework yet. A line reaches the OWASP LLM Top 10 through a kind of duty its law carries, and only where that kind of duty also reaches, on that same line, the NIST framework for the line's own subject. Two controls connect when lines in at least 2 laws reach both. That says the same duties reach both; it does not say the two are alike, or that running either one does what a law asks.

A line placed on a control in the framework for its own subject, whose law carries a kind of duty that reaches another of the three frameworks read line by line, is read against that one as well: every such line, or only those whose wording reaches into it. For these two:

Laws onRead against the NIST CSF 2.0
AIsuch lines on security, robustness, resilience, vulnerabilities and logs
scrapingnot read
news aggregationnot read

Every duty line in the AI laws we track has been read against the framework for its subject.

Sources and licenses

OWASP GenAI Security Project, OWASP Top 10 for LLM Applications 2026, licensed CC BY-SA 4.0. Excerpted: only the first paragraph of each entry's Description is reproduced, verbatim.