PT-2026-28599

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 1.2.22 Description Multiple functions within langchain core.prompts.loading read files from paths embedded in deserialized configuration dictionaries without validating against absolute path injection or directory...

CVE-2026-30304

The AI Code programming assistant, developed by TianGuaDuiZhang , is vulnerable to prompt injection attacks due to its automatic terminal command execution design. The system distinguishes between "safe" and "destructive" commands, automatically executing the former while requiring user approval ...

PT-2026-28397

Name of the Vulnerable Software and Affected Versions AI Code affected versions not specified Description The software’s design, which includes options for executing safe and all commands, is susceptible to prompt injection attacks. The system is intended to automatically execute commands deemed...

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-2026-30304

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-2026-30304: Improper Input Validation

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...

AI Code 安全漏洞

AI Code is a code programming assistant developed by TianGuaDuiZhang. AI Code has a security vulnerability, which stems from the design of automatic terminal command execution, making it susceptible to prompt injection attacks, potentially allowing arbitrary command execution...

PT-2026-28507

Name of the Vulnerable Software and Affected Versions nanobot versions prior to 0.1.6 Description An indirect prompt injection exists in the email channel processing module nanobot/channels/email.py. This allows a remote, unauthenticated attacker to execute arbitrary Large Language Model LLM...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization via the ACP permission resolution process. An attacker can bypass security prompting by providing conflicting tool identity hints in rawInput and metadata, which c...

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...

CVE-2026-32897

OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...

CVE-2026-3587

An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface, leading to full compromise of the device...

CVE-2026-32622

SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology,...

CVE-2026-32247

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-2026-33068

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

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...

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Large Language Models LLMs have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented...

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities

System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model interaction is a first-order security variable: a single...

SUSE CVE-2026-30856

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming...

Leveraging Large Language Models for Trustworthiness Assessment of Web Applications

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem as existing techniques primarily focus on detecting known...