How we found 24 Android vulnerabilities using our open source AI security agent

With the rise of AI in the security space, our team created the GitHub Security Lab Taskflow Agent as a way for security researchers to easily automate, package, and share the AI prompts and workflows that they find effective for their work. In this blog post, I'll share how I created auditing...

EUVD-2026-52592

The Contest Gallery WordPress plugin before 30.0.7 does not perform any capability or nonce check in one of its handlers, allowing any authenticated user down to Subscriber to read the site's entire stored OpenAI prompt history...

SUSE CVE-2026-17351

The fix for CVE-2026-12045 in pgAdmin 4 9.16 required the LLM-supplied query passed to the AI Assistant's executesqlquery tool to parse, via sqlparse, as exactly one non-transaction-control statement before running it inside a BEGIN TRANSACTION READ ONLY wrapper. sqlparse's string-literal lexing...

Linux Distros Unpatched Vulnerability : CVE-2026-46580

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or...

CVE-2026-34837

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, he REST endpoint POST /api/v1/aiassistance/texttools/:id contains an authorization failure. Context data e.g., a group or organization supplied to be used in the AI prompt were not checked if they are accessible f...

CVE-2026-34837

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, he REST endpoint POST /api/v1/aiassistance/texttools/:id contains an authorization failure. Context data e.g., a group or organization supplied to be used in the AI prompt were not checked if they are accessible f...

PT-2026-31424

Name of the Vulnerable Software and Affected Versions Zammad versions prior to 7.0.1 Description Zammad, a web-based open-source helpdesk system, has an authorization failure in the REST endpoint POST /api/v1/ai assistance/text tools/:id. Context data provided for use in the AI prompt was not...

Malicious code in aquasecurityofficial.trivy-vulnerability-scanner (VSCode:https://open-vsx.org)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security b6cab1dae06f51e2aaa57704d8374b6882440070d0796e7b719a85e6f803888b This extension is a compromised version of the offical Trivy VSCode extension available on the Microsoft Marketplace. Versions 1.8.11 and...

MAL-2026-2230 Malicious code in aquasecurityofficial.trivy-vulnerability-scanner (VSCode:https://open-vsx.org)

--- -= Per source details. Do not edit below this line.=- Source: google-open-source-security b6cab1dae06f51e2aaa57704d8374b6882440070d0796e7b719a85e6f803888b This extension is a compromised version of the offical Trivy VSCode extension available on the Microsoft Marketplace. Versions 1.8.11 and...

PT-2026-5959

Name of the Vulnerable Software and Affected Versions Moodle affected versions not specified Description A flaw exists in Moodle due to improper sanitization of AI prompt responses. This allows attackers to inject malicious HTML or script into web pages. Successful exploitation could lead to...

CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

API Attack Awareness: Injection Attacks in APIs – Old Threat, New Surface

Injection attacks are among the oldest tricks in the attacker playbook. And yet they persist. The problem is that the core weakness, trusting user inputs too much, keeps resurfacing in new forms. As organizations have shifted to API-driven architectures and integrated AI systems that consume...

PromptChain: a Decentralized Web3 Architecture for Managing AI Prompts As Digital Assets

We present PromptChain, a decentralized Web3 architecture that establishes AI prompts as first-class digital assets with verifiable ownership, version control, and monetization capabilities. Current centralized platforms lack mechanisms for proper attribution, quality assurance, or fair...