Lucene search
+L

6 matches found

Kitploit
Kitploit
•added 2026/10/15 6:11 p.m.•17 views

markdown-exfil-tester

valtik-markdown-exfil-tester Black-box tester for indirect prompt injection leading to markdown / HTML exfiltration in LLM-backed chatbots. This is the vulnerability class that hit Microsoft 365 Copilot CVE-2025-32711, aka EchoLeak, ChatGPT OpenAI Feb 2026 patch, and Salesforce ForcedLeak. The...

9.3CVSS8.4AI score0.08034EPSS
SaveExploits1
Packet Storm News
Packet Storm News
•added 2026/09/06 12:00 a.m.•28 views

AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve...

5.9AI score
SaveExploits0
CVE
CVE
•added 2026/08/13 1:24 p.m.•35 views

CVE-2026-21832

HCL AION is identified as affected by CVE-2026-21832, where indirect prompt injection can lead to HTML injection in rendered output. The injected markup may be displayed to users, potentially causing unintended behavior or security impact under certain conditions. The provided documents do not sp...

4.3CVSS5.8AI score0.00295EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
•added 2026/06/18 12:00 a.m.•48 views

PT-2026-50691

Name of the Vulnerable Software and Affected Versions Eclipse Theia versions prior to 1.71.0 Description Files matching the pattern .prompts/.prompttemplate in a workspace are automatically loaded, allowing them to override or extend the AI agent's system prompts. This enables indirect prompt...

8.8CVSS6.1AI score0.00507EPSS
SaveExploits0References10
Schneier on Security
Schneier on Security
•added 2025/08/27 11:07 a.m.•30 views

We Are Still Unable to Secure LLMs from Malicious Inputs

Nice indirect prompt injection attack: Bargury's attack starts with a poisoned document, which is shared to a potential victim's Google Drive. Bargury says a victim could have also uploaded a compromised file to their own account. It looks like an official document on company meeting policies. Bu...

7.7AI score
SaveExploits0
Packet Storm
Packet Storm
•added 2010/04/30 12:00 a.m.•30 views

chCounter 3.1.1 SQL Injection / Cross Site Scripting

Exploit Title: chCounter indirect SQL Injection and XSS Vulnerabilities Date: 29.04.2010 Author: Valentin Category: webapps/0day Version: 3.1.1 Tested on: Debian, Apache2, PHP5, MySQL5 CVE : Code : :::::::::::::::::::::::::::::::::::::: 0x1 :::::::::::::::::::::::::::::::::::::: General Informati...

0.6AI score
SaveExploits0
Rows per page
Query Builder