InfoResearchIndustryLLM-specific

OWASP Gen AI Incident & Exploit Round-up, Q2’25

Source: OWASP GenAI Security(opens in a new tab)
Published: July 14, 2025
Record updated: October 9, 2026

Summary

OWASP's Q2 2025 Gen AI Incident & Exploit Round-up (March to June 2025) is a semi-regular roundup of documented exploits and vulnerability research involving generative AI. Its featured entry describes a GPT-4.1 jailbreak via tool poisoning, in which attackers embedded malicious instructions in tool descriptions, causing the model to perform unauthorized actions such as data exfiltration without user awareness. The entry maps the attack to several OWASP Top 10 for LLM categories, including LLM01 Prompt Injection and LLM07 Insecure Plugin Design.

Mitigation

Implement strict validation and sanitization of tool descriptions. Establish permissions and access controls for tool integrations. Monitor AI behavior for anomalies during tool execution. Educate developers on secure integration practices.

Details

Scores and exploitation

Disclosure date: July 14, 2025

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051
AML.T0054

Affected

Vendors: OpenAI

Classification

Attack type: Jailbreak,
Prompt injection
Attack sophistication: Moderate
AI component targeted: Plugin
Impact: Confidentiality,
Integrity,
Safety
Labels: security,
safety

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://genai.owasp.org/2025/07/14/owasp-gen-ai-incident-exploit-round-up-q225/?utm_source=rss&utm_medium=rss&utm_campaign=owasp-gen-ai-incident-exploit-round-up-q225

First tracked: March 13, 2026 at 12:56 PM ET, from OWASP GenAI Security

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)

Topics

Prompt injection and jailbreaks

Summary

Mitigation

Topics

Related items