PT-2026-96188

Name of the Vulnerable Software and Affected Versions @aborruso/ckan-mcp-server affected versions not specified Description Tools such as ckan package search, sparql query, and ckan datastore search sql accept a base url or server url parameter that allows making HTTP requests to arbitrary...

PISmith: Reinforcement Learning-Based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we...

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw

The rapid evolution of Large Language Models LLMs into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to execute complex workflows. This level of access creates...

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent...

OpenClaw AI Agent Flaws Could Enable Prompt Injection and Data Exfiltration

China's National Computer Network Emergency Response Technical Team CNCERT has issued a warning about the security risks stemming from the use of OpenClaw formerly Clawdbot and Moltbot, an open-source and self-hosted autonomous artificial intelligence AI agent. In a post shared on WeChat, CNCERT...

CVE-2026-32715

CVE-2026-32715 | AnythingLLM in versions up to 1.11.1 has a privilege bypass where two generic system-preferences endpoints expose manager-level access, bypassing admin-only restrictions. This allows a manager to read plaintext SQL database credentials and overwrite admin-only global settings (e....

CVE-2026-32715 AnythingLLM Manager Privilege Bypass Allows Access to Admin-Only System Preferences

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, The two generic system-preferences endpoints allow manager role access, while every other surface that touches the same settings is restricted to admi...

CVE-2026-32715 AnythingLLM Manager Privilege Bypass Allows Access to Admin-Only System Preferences

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, The two generic system-preferences endpoints allow manager role access, while every other surface that touches the same settings is restricted to admi...

CVE-2026-32715 AnythingLLM Manager Privilege Bypass Allows Access to Admin-Only System Preferences

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, The two generic system-preferences endpoints allow manager role access, while every other surface that touches the same settings is restricted to admi...

PT-2026-25396

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. In 1.11.1 and earlier, The two generic system-preferences endpoints allow manager role access, while every other surface that touches the same settings is restricted to admi...

CVE-2026-32247 Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

CVE-2026-32247 Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

GHSA-GG5M-55JJ-8M5G Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Summary Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabels were concatenated directly into Cypher label expressions without validation. In...

Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Autonomous Large Language Model LLM agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

EUVD-2026-11205

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-2026-31854

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...