CVE-2026-12045

A flaw was found in the pgAdmin 4 AI Assistant. An attacker with the ability to influence database content that the assistant reads can exploit a transaction bypass vulnerability through prompt injection. This allows the attacker to execute arbitrary SQL queries with the privileges of the pgAdmin...

CVE-2026-46580

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 extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

CVE-2026-46580

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 extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

EUVD-2026-37899

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 extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-46580

Theia before v1.71.0 loads files matching .prompts/*.prompttemplate from a workspace, allowing attacker-controlled content to override the AI agent’s system prompts (indirect prompt injection). This enables attack chains with untrusted workspaces, potentially causing data exfiltration via Markdow...

CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

EUVD-2026-37898

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

CVE-2026-44688

The vulnerability CVE-2026-44688 affects Eclipse Theia versions prior to 1.71.0. The AI chat agent processes workspace file and directory names as part of its prompt context without distinguishing them from system instructions, enabling indirect prompt injection when an attacker uses adversarial ...

CVE-2026-55743

OpenHuman desktop agent (before 0.54.0, fixed in 0.56.0) contains two policy flaws in src/openhuman/security/policy.rs that bypass the shell allowlist, enabling remote code execution via indirect prompt injection. First, is_args_safe() blocks -exec and -ok while not blocking -execdir/-okdir (whic...

Reconstructing AI activity in investigations

AI systems are now part of everyday work. Investigators need a consistent way to reconstruct what happened within them. Security teams are already investigating activity involving Microsoft 365 Copilot and Azure AI services—from prompt injection attempts to unexpected data access. Those signals a...

Reconstructing AI activity in investigations

AI systems are now part of everyday work. Investigators need a consistent way to reconstruct what happened within them. Security teams are already investigating activity involving Microsoft 365 Copilot and Azure AI services—from prompt injection attempts to unexpected data access. Those signals a...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

Large language model LLM agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments. This transition changes the nature of security risk. In agentic settings, failures are no longer limited to unsafe...

State of Agentic AI Security and Governance

An OWASP white paper analyzing the security, governance, and risk management considerations surrounding agentic AI systems, including autonomous decision-making, tool access, prompt injection, data protection, and organizational oversight. This is version 2.01...

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

AI-powered agents are increasingly embedded in continuous integration and continuous delivery/deployment CI/CD pipelines to autonomously review pull requests PRs, triage issues, and maintain codebases. These agents ingest untrusted content while operating with elevated repository permissions,...

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

OpenAI has begun rolling out a new Lockdown Mode to ChatGPT for eligible personal accounts to reduce the risk of data exfiltration arising from prompt injection attacks. The feature is primarily designed for people and organizations that handle sensitive data and require stricter protection...

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector...

CVE-2026-30615

A prompt injection vulnerability in Windsurf 1.9544.26 allows remote attackers to execute arbitrary commands on a victim system. When Windsurf processes attacker-controlled HTML content, malicious instructions can cause unauthorized modification of the local MCP configuration and automatic...

CVE-2026-41318

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to version 1.12.1, AnythingLLM's in-chat markdown renderer has an unsafe custom rule for images that interpolates the markdown image's alt text into an HTML alt="..."...