OWASP Top 10 for LLM Applications 2026
LLM07:2026 Misinformation
None of its primary CWEs is specific to it, so ShieldMap does not tag advisories with it, and 1 technique page explains how the attacks work.
OWASP Top 10 for Agentic Applications
- ●ASI08:2026 Cascading FailuresIncorrect state or evidence produced by one agent and trusted by another propagates misinformation across a multi-agent workflow into a compounding, high-impact failure (Cross-Agent Misinformation Propagation; Cross-Agent Trust Failure)
- ●ASI09:2026 Human-Agent Trust ExploitationHumans and downstream systems that treat fluent, confident model output as authoritative are the exploited trust surface this entry's overreliance framing describes (Unsupported or False Decision Support)
- ●ASI10:2026 Rogue AgentsAn agent that falsifies task completion or fabricates evidence to mislead downstream trust matches this entry's forged-evidence and false-completion failure modes (Forged or Misattributed Evidence; Fabricated Task Completion)
CWE weaknesses
- ●CWE-1426 Improper Validation of Generative AI OutputIncorrect, unsupported, or misleading model output is trusted and acted upon without verification, the entry's core weakness.
- ○CWE-349 Acceptance of Extraneous Untrusted Data With Trusted DataA downstream agent accepts fabricated or misattributed upstream output as trusted evidence, a cross-agent trust failure.
- ○CWE-494 Download of Code Without Integrity CheckA hallucinated package name is installed without any integrity or authenticity check, the slopsquatting failure.
- ○CWE-1427 Improper Neutralization of Input Used for LLM PromptingAdversarially crafted inputs induce false or misleading output, the input-side manipulation behind adversarially induced misinformation.
MITRE ATLAS tactics
- ●AML.TA0011 ImpactFalse output that is trusted and acted upon causes financial loss, security incidents, safety risks, and operational disruption, as when a fabricated alert derails operations.
- ○AML.TA0003 Resource DevelopmentAttackers publish malicious packages under names the model is known to hallucinate, staging a supply-chain trap keyed to the confabulation.
- ○AML.TA0004 Initial AccessA hallucinated dependency, once recommended and installed by a trusting developer, becomes an AI supply-chain foothold.
- ○AML.TA0001 AI Attack AdaptationAdversaries craft inputs that steer the model toward specific false claims, an induced-misinformation staging step.
NIST AI 600-1 risks
- ●NIST Information IntegrityThe entry concerns GenAI producing false or misleading information that degrades human decisions, the definition of this misinformation risk.
- ●NIST ConfabulationConfabulation, NIST's term for confidently stated but false output, is named as a primary source of the misinformation.
- ●NIST Human-AI ConfigurationAutomation bias and overreliance are called a key factor, addressed by calibrating human and system trust.
- ○NIST Information SecurityAdversarially induced misinformation and false alerts can cause security incidents and operational disruption.
- ○NIST Value Chain and Component IntegrationHallucinated dependencies and unvalidated third-party tool outputs are value-chain integration risks.
NIST AI RMF categories
- ●MEASURE 2 evaluate trustworthinessThe entry's defense is evaluation-centric, using groundedness and consistency checks, misinformation monitoring and testing, and continuous adversarial evaluation to measure the validity, reliability, and accuracy that misinformation threatens.
- ○MEASURE 1 methods & metricsVerification signals such as groundedness and consistency checks replace naive model confidence as the metric for whether a claim can be trusted before action.
- ○MEASURE 3 track risks over timeClaims, evidence, and outcomes are logged and adversarial scenarios tested so misinformation is tracked over time.
- ○MANAGE 1 prioritize & respond to risksRuntime verification and approval workflows for high-impact actions, together with blast-radius limits, are impact-prioritized response controls.
OWASP GenAI Data Security
- ●DSGAI21 Disinformation & Integrity Attacks via Data PoisoningDeliberately injected content makes the system surface false or forged material as authoritative, the core disinformation-via-poisoning mechanism.
- ○DSGAI05 Data Integrity & Validation FailuresBiased or corrupted source data and unvalidated ingestion are root causes that let misinformation enter and spread.
- ○DSGAI06 Tool, Plugin & Agent Data Exchange RisksUnvalidated tool outputs and cross-agent exchange propagate false information, so tool calls need semantic validation.
OWASP AIVSS agentic risks
- ●AIVSS-3 Agent Cascading FailuresIncorrect state or evidence produced by one agent and trusted by another propagates across a multi-agent workflow into a compounding, high-impact failure.
- ○AIVSS-1 Agentic AI Tool MisuseBecause model outputs drive tool calls, an incorrect state inference triggers unintended actions unless invocations are validated against real-world state and intent.
- ○AIVSS-7 Insecure Agent Critical Systems InteractionA false conclusion, such as wrongly approving a refund or firing a false alert, drives an automated high-impact action that causes financial loss or operational disruption.
CSA AI Controls Matrix domains
- ●AIS Application & Interface Security
- ○TVM Threat & Vulnerability Management
- ○LOG Logging and Monitoring
- ○STA Supply Chain Management, Transparency, and Accountability
Mappings and their reasons from the OWASP Top 10 for LLM Applications 2026, Appendix A (OWASP GenAI Security Project), shared under CC BY-SA 4.0. Mappings restructured as data; the ATT&CK section and the AICM relevance text left out. Navigation, not a compliance claim.