Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection across Attack Surfaces and Model Safety Tiers

We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate ASR; we localize the pipeline stage at which each model's defense activates. We instrument every run with a cryptographic canary token...

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-30308: Improper Control of Generation of Code

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-30306: Improper Control of Generation of Code

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

SakaDev 安全漏洞

SakaDev is an AI-driven software development assistant developed by Rahman Azhar. SakaDev has a security vulnerability, which stems from defects in the design of automatic terminal command execution. This vulnerability makes it susceptible to prompt injection attacks, potentially allowing arbitra...

CVE-2026-30306

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-30306

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-29119

Name of the Vulnerable Software and Affected Versions SakaDev affected versions not specified Description SakaDev’s automatic terminal command execution feature, designed with ‘safe’ and ‘all commands’ options, is prone to prompt injection attacks. The system aims to automatically execute command...

PT-2026-29120

Name of the Vulnerable Software and Affected Versions HAI Build Code Generator affected versions not specified Description The software’s design for automatic terminal command execution, offering ‘Execute safe commands’ and ‘Execute all commands’ options, is susceptible to prompt injection attack...

CVE-2026-30306

In its design for automatic terminal command execution, SakaDev offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30308

In its design for automatic terminal command execution, HAI Build Code Generator offers two options: Execute safe commands and Execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a...

CVE-2026-30306

The AI-driven software development assistant SakaDev is vulnerable to prompt injection attacks due to a design flaw in its automatic terminal command execution feature. While the system is intended to automatically execute "safe" commands and require user approval for destructive ones, an attacke...

HAI Builds Code Generator 安全漏洞

HAI Builds Code Generator is an AI-driven software requirement generation and management tool open-sourced by Presidio INC. HAI Builds Code Generator has a security vulnerability, which stems from defects in the design of automatic terminal command execution. This vulnerability makes it susceptib...

CVE-2026-33654

nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module nanobot/channels/email.py, allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions and subsequently, system tools without...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-33654

nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module nanobot/channels/email.py, allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions and subsequently, system tools without...

CVE-2026-33654 Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling

nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module nanobot/channels/email.py, allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions and subsequently, system tools without...

CVE-2026-33654 Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling

nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module nanobot/channels/email.py, allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions and subsequently, system tools without...

CVE-2026-33654

Summary of CVE-2026-33654 : nanobot (personal AI assistant) contains an indirect prompt injection vulnerability in the email channel processing module (nanobot/channels/email.py) prior to version 0.1.6. An unauthenticated remote attacker can send a malicious email to the bot’s monitored address, ...