CVE-2026-40117: Missing Authorization

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, readskillfile in skilltools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skillpath parameter. Unlike filetools.readfile which enforces workspace boundary confinement, and unlike runskillscript...

PT-2026-33637

Impact Lower-trust background runtime output is injected into trusted System: events, and local async exec completion misses the intended exec-event downgrade. Lower-trust runtime/background output could be promoted into trusted System events, allowing prompt-injection into later agent turns...

Security Concerns in Generative AI Coding Assistants: Insights from Online Discussions on GitHub Copilot

Generative Artificial Intelligence GenAI has become a central component of many development tools e.g., GitHub Copilot that support software practitioners across multiple programming tasks, including code completion, documentation, and bug detection. However, current research has identified...

PT-2026-33638

Impact Authenticated /hooks/wake and mapped wake payloads are promoted into the trusted System: prompt channel. An authenticated wake hook or mapped wake payload could be promoted into the trusted System prompt channel instead of an untrusted event. OpenClaw is a user-controlled local assistant...

PT-2026-31786

Name of the Vulnerable Software and Affected Versions PraisonAIAgents versions prior to 1.5.128 Description PraisonAIAgents is a multi-agent teams system. The read skill file function in skill tools.py allows reading arbitrary files from the filesystem due to an unrestricted skill path parameter...

CVE-2026-40112: Improper Neutralization of Input During Web Page Generation

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the Flask API endpoint in src/praisonai/api.py renders agent output as HTML without effective sanitization. The sanitizehtml function relies on the nh3 library, which is not listed as a required or optional dependency in pyproject.toml...

LangChain has incomplete f-string validation in prompt templates

LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate...

GHSA-926X-3R5X-GFHW LangChain has incomplete f-string validation in prompt templates

LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate...

CVE-2026-34837 Zammad is miissing authorization in AI assistance controller for context data used in text tools

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, he REST endpoint POST /api/v1/aiassistance/texttools/:id contains an authorization failure. Context data e.g., a group or organization supplied to be used in the AI prompt were not checked if they are accessible f...

PT-2026-31716

Name of the Vulnerable Software and Affected Versions LangChain versions prior to 0.3.84 and prior to 1.2.28 Description LangChain's f-string prompt-template validation was incomplete, allowing attribute access and indexing expressions in templates for DictPromptTemplate and ImagePromptTemplate...

CVE-2026-35021

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $ or backtick expressions in...

GrafanaGhost Vulnerability Allows Data Theft via AI Injection

GrafanaGhost is a critical vulnerability in Grafana’s AI components that uses indirect prompt injection and protocol-relative URL bypasses to exfiltrate data...

CVE-2026-35487 text-generation-webui has a Path Traversal in load_prompt() — .txt file read without authentication

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35487 text-generation-webui has a Path Traversal in load_prompt() — .txt file read without authentication

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35487

text-generation-webui (open-source web interface for LLMs) before version 4.3 is affected by an unauthenticated path traversal in load_prompt(), allowing reading any .txt file on the server and returning its contents in the API response. Impact is limited to read access of server-side .txt files;...

EUVD-2026-19672

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35487

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models LLMs in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003...

Text Generation Web UI 路径遍历漏洞

Text Generation Web UI is a local AI UI interface developed by oobabooga’s individual developers. Versions of Text Generation Web UI prior to 4.3 contained a path traversal vulnerability. This vulnerability stemmed from an unauthenticated path traversal vulnerability in the loadprompt function,...