Path 01
Ask questions where the model lacks reliable context or current facts.
OWASP LLM Top 10 guide
LLM09:2025
Misinformation
Misinformation occurs when an AI system produces false, unsupported, outdated, or misleading output that users or downstream systems treat as reliable.
Step 01
Input
Step 02
Model
Step 03
Tool / Data
Step 04
Impact
What it is
The application does not give users enough provenance, confidence, grounding, review, or workflow limits to separate supported answers from plausible but wrong output.
Why it matters
Misinformation can affect customer support, legal and security decisions, clinical or financial workflows, executive reporting, and customer trust in product output.
Failure path
How it usually fails.
A useful review breaks this chain before the system reaches production data, tools, or customer-facing decisions.
Path 02
Exploit weak grounding, missing citations, ambiguous prompts, or overconfident response style.
Path 03
Push users or systems to act on unsupported output.
Defenses
Controls worth checking.
The strongest controls are enforced outside the model and can be retested after a prompt, model, or workflow change.
Control 01
Ground high-impact answers
Require citations, source snippets, freshness indicators, and answer abstention for workflows where unsupported output creates risk.
Control 02
Constrain claims
Use domain-specific answer policies, confidence thresholds, and review paths for legal, security, safety, financial, or customer-impacting claims.
Control 03
Design for uncertainty
Make the product show what is known, what is inferred, and what needs human review.
Signals to review
- Answers with no source for factual claims.
- Overconfident output when retrieval returned weak or empty context.
- Users copying AI output into high-impact workflows without review.
Questions for your team
- Which answers require source grounding?
- Does the model clearly abstain when context is missing?
- Where could a wrong answer create a customer, security, or legal issue?