PraisonAI has Template Injection in Agent Tool Definitions

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user inpu...

CVE-2026-32901

Rejected reason: This CVE ID has been rejected...

PT-2026-27235

OpenClaw before 2026.3.2 contains a semantic drift vulnerability in node system.run approval hardening that rewrites wrapper command argv, allowing execution of unintended local scripts. Attackers who can influence wrapper argv and place malicious files in the approved working directory can execu...

GHSA-H3RM-6X7G-882F OpenClaw's Node system.run approval hardening wrapper semantic drift can execute unintended local scripts

Summary In [email protected], node system.run approval-path hardening rewrote wrapper command argv in a way that changed execution semantics. A command shown/approved as a shell payload for example echo SAFE could execute a different local script when wrapper argv were rewritten. Affected Package...

OpenClaw's Node system.run approval hardening wrapper semantic drift can execute unintended local scripts

Summary In [email protected], node system.run approval-path hardening rewrote wrapper command argv in a way that changed execution semantics. A command shown/approved as a shell payload for example echo SAFE could execute a different local script when wrapper argv were rewritten. Affected Package...