LLM02:2025: Sensitive Information Disclosure
LLMs leak training data, system prompts, customer PII, secrets, or proprietary logic through inference or memorized content.
How it's found
Found by probing model responses with targeted extraction prompts to check for training-data leakage, memorized secrets, or system-prompt disclosure.
Standards mapping
How TurboPentest tests for this
TurboPentest's automated black-box pentest actively probes for Exposure of Sensitive Information to an Unauthorized Actor using Nuclei's exposure templates (exposed configuration files, admin panels, API keys, .env and .git paths), with no source code required. Connecting a GitHub repo adds white-box confirmation from IntegSec's Opengrep SAST rule pack, which carries 8 dedicated rules for this weakness.
Tools: Nuclei
Frequently asked questions
What is LLM02:2025 Sensitive Information Disclosure?
LLMs leak training data, system prompts, customer PII, secrets, or proprietary logic through inference or memorized content.
How do you find Sensitive Information Disclosure?
Found by probing model responses with targeted extraction prompts to check for training-data leakage, memorized secrets, or system-prompt disclosure.
Which CWEs map to LLM02:2025?
LLM02:2025 maps to CWE-200, CWE-359.
Does TurboPentest test for Sensitive Information Disclosure?
TurboPentest's automated black-box pentest actively probes for Exposure of Sensitive Information to an Unauthorized Actor using Nuclei's exposure templates (exposed configuration files, admin panels, API keys, .env and .git paths), with no source code required. Connecting a GitHub repo adds white-box confirmation from IntegSec's Opengrep SAST rule pack, which carries 8 dedicated rules for this weakness.
Related OWASP categories
- OWASP Top 10 for LLM ApplicationsLLM01:2025: Prompt Injection
- OWASP Top 10 for LLM ApplicationsLLM03:2025: Supply Chain
- OWASP Top 10 for LLM ApplicationsLLM04:2025: Data and Model Poisoning
- OWASP Top 10 for LLM ApplicationsLLM05:2025: Improper Output Handling
- OWASP Top 10 for LLM ApplicationsLLM06:2025: Excessive Agency
- OWASP Top 10 for LLM ApplicationsLLM07:2025: System Prompt Leakage
Written and reviewed by
Michel Chamberland - Founder & CEO, IntegSec
CISSP, OSCP, OSCE, CEH, GIAC, CCSK · 20+ years in offensive security
Michel has spent 20+ years on offensive security teams including IBM X-Force Red and Trustwave SpiderLabs, leading penetration tests, red team engagements, and breach response for Fortune 500 customers. He is the founder of IntegSec and the architect of TurboPentest.
Find these issues before an attacker does
TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.
Start a pentest