Improper Output Handling (LLM05)
Downstream systems trust LLM output and execute it without validation, leading to traditional injection vulnerabilities (XSS, SQL injection, command execution) being introduced through LLM-generated payloads.
- Rank
- LLM05 of 10
- In the check
- Not cited directly by a question
What it looks like in practice
Three shapes this risk takes in real deployments.
Example 1
An LLM writes a SQL query that's executed without parameterization.
Example 2
An LLM-generated HTML response is rendered without escaping, leading to stored XSS.
Example 3
An LLM writes shell commands that an automation framework executes.
Controls that close it
The controls the check looks for when this entry applies.
Treat LLM output as untrusted input to downstream systems
Output schema validation
Sandboxing for code-execution use cases
Output filtering and re-validation
Where the check cites it
The AI Posture Check cites OWASP LLM Top 10, including this entry, when placing you at Crawl, Walk, Run or Sprint.
The questions cite the control frameworks a regulator would expect you to hold: NIST AI RMF, ISO 42001 and the OWASP LLM Top 10. Your stage on the check is a starting point for an EU AI Act conformity review, not a substitute for one.
Other frameworks the check cites
Score yourself against this framework.
Five questions, each citing its source. You get your stage, your place on the chart and the one move that matters next.
- A few minutes for most people
- Free, from CWS
- Your stage, the chart and the next move, by email or live with an engineer