1330 matches found
PT-2025-41975
A prompt injection vulnerability exists in Windsurft version 1.10.7 in Write mode using SWE-1 model. It is possible to create a file name that will be appended to the user prompt causing Windsurf to follow its instructions...
PromptLocate: Localizing Prompt Injection Attacks
Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instructions and data. Localizing the injected prompt within contaminated data is...
OpenAI’s Guardrails Can Be Bypassed by Simple Prompt Injection Attack
Just weeks after its release, OpenAI’s Guardrails system was quickly bypassed by researchers. Read how simple prompt injection attacks fooled the system’s AI judges and exposed an ongoing security concern for OpenAI...
Countermind: A Multi-Layered Security Architecture for Large Language Models
The security of Large Language Model LLM applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fai...
Exploiting Web Search Tools of AI Agents for Data Exfiltration
Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...
Towards Reliable and Practical LLM Security Evaluations Via Bayesian Modelling
Before adopting a new large language model LLM architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully comparable, relying on heuristic inputs or employing metrics that fai...
Imperceptible Jailbreaking against Large Language Models
Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications e.g., non-semantic suffixes. In this paper, we introduce imperceptible jailbreaks that exploit a...
CVE-2025-59944
Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...
CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible
Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...
CVE-2025-59944
Cursor IDE versions 1.6.23 and earlier are affected by a vulnerability in how sensitive files are protected (notably /.cursor/mcp.json). The issue arises from case-sensitive checks that can be bypassed, allowing an attacker to modify sensitive files via prompt injection and achieve remote code ex...
CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible
Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...
CVE-2025-59944 Cursor IDE: Sensitive File Overwrite Bypass is Possible
Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...
EUVD-2025-32373
Cursor is a code editor built for programming with AI. Versions 1.6.23 and below contain case-sensitive checks in the way Cursor IDE protects its sensitive files e.g., /.cursor/mcp.json, which allows attackers to modify the content of these files through prompt injection and achieve remote code...
EUVD-2025-26607
Malicious code in bioql PyPI...
EUVD-2024-48089
Malicious code in bioql PyPI...
EUVD-2024-31893
Malicious code in bioql PyPI...
EUVD-2025-27052
Malicious code in bioql PyPI...
EUVD-2025-19434
Malicious code in bioql PyPI...