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...

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...

CVE-2026-31854 Cursor Affected by Arbitrary Code Execution via Prompt Injection and Whitelist Bypass

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...

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 Affected by Arbitrary Code Execution via Prompt Injection and Whitelist Bypass

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 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...