EUVD-2026-11245

Cursor is a code editor built for programming with AI. Prior to 2.0 ,if a visited website contains maliciously crafted instructions, the model may attempt to follow them in order to “assist” the user. When combined with a bypass of the command whitelist mechanism, such indirect prompt injections...

CVE-2026-31854

Cursor is a code editor for programming with AI. Prior to 2.0, if a visited website contains malicious instructions, the model may follow them to “assist” the user. When combined with a bypass of the command whitelist, indirect prompt injections could cause automatic command execution without use...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

PT-2026-24720

Name of the Vulnerable Software and Affected Versions OpenClaw Agent Platform version 2026.2.6 Description A remote code execution RCE issue exists in OpenClaw Agent Platform version 2026.2.6. This allows attackers to execute arbitrary code through a Request-Side prompt injection attack. The...

PT-2026-24747

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2.0 Description Cursor is a code editor designed for programming with AI. Prior to version 2.0, if a visited website contained maliciously crafted instructions, the model could attempt to follow them to assist the user...

CVE-2026-30741

The OpenClaw Agent Platform (version v2026.2.6 and earlier) is vulnerable to Remote Code Execution (RCE) due to a Request-Side prompt injection attack. The root cause is a lack of integrity validation for upstream API requests, which enables request-stream poisoning . This allows an attacker to t...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents Via Causal Attribution of Tool Invocations

LLM agents are highly vulnerable to Indirect Prompt Injection IPI, where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination problem, which often fails to generalize to unseen payloads. We...

CVE-2026-31854: Improper Neutralization of Special Elements used in an OS Command

Cursor is a code editor built for programming with AI. Prior to 2.0 ,if a visited website contains maliciously crafted instructions, the model may attempt to follow them in order to “assist” the user. When combined with a bypass of the command whitelist mechanism, such indirect prompt injections...

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-30741: Improper Control of Generation of Code

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

GO-2026-4638 WeKnora Vulnerable to Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection in github.com/Tencent/WeKnora

WeKnora Vulnerable to Tool Execution Hijacking via Ambigous Naming Convention In MCP client and Indirect Prompt Injection in github.com/Tencent/WeKnora...

CVE-2026-2364 CODESYS Installer TOCTOU Privilege Escalation

If a legitimate user confirms a self-update prompt or initiate an installation of a CODESYS Development System, a low privileged local attacker can gain elevated rights due to a TOCTOU vulnerability in the CODESYS installer...

Exploit for Code Injection in Anthropic Claude_Code

Claude Code: MCP Tool Confirmation Prompt Misrepresentation !...

poc-factory-sample-output

Prompt Injection Guardrails Introduction In the rapidly e...

CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

CVE-2026-29783

The shell tool within GitHub Copilot CLI versions prior to and including 0.0.422 can allow arbitrary code execution through crafted bash parameter expansion patterns. An attacker who can influence the commands executed by the agent e.g., via prompt injection through repository files, MCP server...