CVE-2026-27001 OpenClaw: Unsanitized CWD path injection into LLM prompts

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example...

CVE-2026-27001 OpenClaw: Unsanitized CWD path injection into LLM prompts

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example...

CVE-2026-27001

OpenClaw (npm package) before version 2026.2.15 embeds the current working directory (workspace path) into the agent system prompt without sanitization. If the directory name contains control/format characters (e.g., newlines, Unicode bidi/zero-width markers), an attacker could craft inputs to br...

CVE-2026-27001 OpenClaw: Unsanitized CWD path injection into LLM prompts

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example...

CVE-2026-26321 OpenClaw has a local file disclosure via sendMediaFeishu in Feishu extension

OpenClaw is a personal AI assistant. Prior to OpenClaw version 2026.2.14, the Feishu extension previously allowed sendMediaFeishu to treat attacker-controlled mediaUrl values as local filesystem paths and read them directly. If an attacker can influence tool calls directly or via prompt injection...

CVE-2026-24764

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764

OpenClaw (formerly Clawdbot) is affected by a prompt-injection vulnerability (CVE-2026-24764) when Slack integration is enabled. In versions 2026.2.2 and earlier, Slack channel metadata (topic/description) could be incorporated into the model’s system prompt, increasing the surface for injection....

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

OpenClaw formerly Clawdbot is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata topic/description can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven...

Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard Vs. Reasoning Models

As Large Language Models LLMs are increasingly integrated into automated decision-making pipelines, specifically within Human Resources HR, the security implications of Indirect Prompt Injection IPI become critical. While a prevailing hypothesis posits that "Reasoning" or "Chain-of-Thought" Model...

OpenClaw: Unsanitized CWD path injection into LLM prompts

Overview OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example newlines or Unicode bidi/zero-width markers, those...

GHSA-2QJ5-GWG2-XWC4 OpenClaw: Unsanitized CWD path injection into LLM prompts

Overview OpenClaw embedded the current working directory workspace path into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters for example newlines or Unicode bidi/zero-width markers, those...

PT-2026-23529

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.14 Description The Feishu extension in OpenClaw is susceptible to server-side request forgery SSRF. This allows attackers to retrieve content from attacker-controlled remote URLs without proper SSRF protection...

PT-2026-20963

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.15 Description OpenClaw embedded the current working directory workspace path into the agent system prompt without proper sanitization. An attacker could potentially exploit this by creating a directory with...

GHSA-G27F-9QJV-22PM OpenClaw log poisoning (indirect prompt injection) via WebSocket headers

Summary In openclaw versions prior to 2026.2.13, OpenClaw logged certain WebSocket request headers including Origin and User-Agent without neutralization or length limits on the "closed before connect" path. If an unauthenticated client can reach the gateway and send crafted header values, those...

OpenClaw log poisoning (indirect prompt injection) via WebSocket headers

Summary In openclaw versions prior to 2026.2.13, OpenClaw logged certain WebSocket request headers including Origin and User-Agent without neutralization or length limits on the "closed before connect" path. If an unauthenticated client can reach the gateway and send crafted header values, those...

OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Summary When the Slack integration is enabled, Slack channel metadata topic/description could be incorporated into the model's system prompt. Impact Prompt injection is a documented risk for LLM-driven systems. This issue increased the injection surface by allowing untrusted Slack channel metadat...

GHSA-782P-5FR5-7FJ8 OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Summary When the Slack integration is enabled, Slack channel metadata topic/description could be incorporated into the model's system prompt. Impact Prompt injection is a documented risk for LLM-driven systems. This issue increased the injection surface by allowing untrusted Slack channel metadat...

Microsoft Finds “Summarize with AI” Prompts Manipulating Chatbot Recommendations

New research from Microsoft has revealed that legitimate businesses are gaming artificial intelligence AI chatbots via the "Summarize with AI" button that's being increasingly placed on websites in ways that mirror classic search engine poisoning SEO. The new AI hijacking technique has been...