Robot Explains Gallery

OWASP Top 10 for LLMs (2025 Archive)

Archived: the earlier (2025) OWASP Top 10 for LLMs poster set.

These posters were based on the earlier OWASP Top 10 for LLM Applications (2025). They're kept for reference; the current edition is the 2026 set.

Difficulty: IntermediatePosters: 10Audience: Intermediate

These posters were based on the earlier OWASP LLM Top 10. A 2026 update is in progress. See the current 2026 set →

⇩ Download all posters (ZIP)

Advanced visual cards for older learners & grown-ups

Unlike the rest of the library, these are poster cards rather than full lessons, a friendly visual interpretation of the OWASP Top 10 for LLM applications, for awareness and discussion. They're best for older learners and grown-ups, and are not a replacement for the official OWASP guidance.

New here? Start with: What is OWASP? 🎮 Play the Defender Game

Infographic: Prompt Injection. When sneaky instructions try to trick the robot into breaking its rules.
#1

Prompt Injection

When sneaky instructions try to trick the robot into breaking its rules.

View poster →
Infographic: Sensitive Information Disclosure. When the robot accidentally spills a secret it should have kept.
#2

Sensitive Information Disclosure

When the robot accidentally spills a secret it should have kept.

View poster →
Infographic: Supply Chain Vulnerabilities. Sometimes bad ingredients sneak into the robot's toolbox.
#3

Supply Chain Vulnerabilities

Sometimes bad ingredients sneak into the robot's toolbox.

View poster →
Infographic: Data and Model Poisoning. When the robot learns from bad examples and picks up wrong ideas.
#4

Data and Model Poisoning

When the robot learns from bad examples and picks up wrong ideas.

View poster →
Infographic: Improper Output Handling. When an app trusts the robot's answer without double-checking it.
#5

Improper Output Handling

When an app trusts the robot's answer without double-checking it.

View poster →
Infographic: Excessive Agency. When the robot is allowed to do more than it really should.
#6

Excessive Agency

When the robot is allowed to do more than it really should.

View poster →
Infographic: System Prompt Leakage. When the robot's secret instructions slip out for everyone to see.
#7

System Prompt Leakage

When the robot's secret instructions slip out for everyone to see.

View poster →
Infographic: Vector and Embedding Weaknesses. When the robot's memory lookup gets confused or tricked.
#8

Vector and Embedding Weaknesses

When the robot's memory lookup gets confused or tricked.

View poster →
Infographic: Misinformation. When the robot says something wrong but sounds very sure.
#9

Misinformation

When the robot says something wrong but sounds very sure.

View poster →
Infographic: Unbounded Consumption. When the robot uses way too much and slows everything down.
#10

Unbounded Consumption

When the robot uses way too much and slows everything down.

View poster →