OWASP LLM
LLM02 · Sensitive Information Disclosure
The model or application reveals secrets, personal data or proprietary information through outputs.
OWASP Top 10 for LLM Applications (2025)
Mitigations
- Minimise sensitive data in prompts, context and training
- Output filtering / DLP on responses
- Per-user access control on retrieval
Detections 5
- AI agent transcripts or credential stores held open by an unexpected process
- Model output contains markdown images or reference links to external hosts
- Entra ID user or admin consent granted to an AI application
- Endpoint process talking to an AI API that is not on the approved list
- Web proxy: requests to AI model APIs that do not come from the approved AI gateway
Related techniques
- LLM07 System Prompt Leakage OWASP LLM
- AML.T0024 Exfiltration via AI Inference API MITRE ATLAS
- AML.T0086 Exfiltration via AI Agent Tool Invocation MITRE ATLAS
In the news
-
OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms
Dragos reported attackers stole data from three AI inference providers for months, including requests flagged Zero Data Retention; OpenRouter dropped the three providers.
ReviewReview data retention settings and provider routing used with AI inference gateways
-
A Single Malicious Webpage Let Researchers Hijack Meta Muse and Access Private Chats
Researchers showed a malicious webpage could extract a Meta Muse user's private chats and stored memories without an approval prompt, in a lab demonstration.
ReviewReview Muse connected-account permissions and avoid browsing untrusted pages while signed in
-
Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
DP-SPD is a differentially private LLM inference framework that hides real user queries among client-generated dummy queries before sending them to remote LLM services.
-
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
Researchers show shuffled obfuscation of LLM KV caches is weaker than claimed, since repeated tokens reduce the effective state space and allow token recovery.
ReviewReview KV cache sharing and obfuscation assumptions in shared LLM serving infrastructure
-
GapLeak: When Privacy-Preserving LLM-based Web Agents Become a Privacy Risk
GapLeak describes how a website can make privacy-preserving LLM web agents escalate to unauthorized sources and disclose sensitive data without prompt injection.
Tools
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.