EUVD-2025-208315

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

GHSA-V2XR-WVRV-P969 RAGAS has an Arbitrary File Read vulnerability

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

OpenClaw 操作系统命令注入漏洞

OpenClaw is an open-source intelligent artificial assistant. OpenClaw has a vulnerability related to operating system command injection. This vulnerability stems from the exec-approvals permission list validation mechanism, which checks the argv tokens in a pre-expanded manner but actually execut...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class within Exploding Gradients RAGAS versions v0.2.3 to v0.2.14 . The flaw is caused by insufficient validation and sanitization of URLs provided in the retrieved_contexts parameter during the processing of multimodal input...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

PT-2026-23468

Name of the Vulnerable Software and Affected Versions Exploding Gradients RAGAS versions 0.2.3 through 0.2.14 Description An arbitrary file read issue exists in the ImageTextPromptValue class. This is due to insufficient validation and sanitization of URLs provided in the retrieved contexts...

CVE-2026-28463: Improper Neutralization of Special Elements used in an OS Command

OpenClaw versions prior to 2026.2.14 contain an arbitrary file read vulnerability in the exec-approvals allowlist validation that checks pre-expansion argv tokens but executes using real shell expansion. Attackers with authorization or through prompt-injection attacks can exploit safe binaries li...

CVE-2026-28451: Server-Side Request Forgery (SSRF)

OpenClaw versions prior to 2026.2.14 contain server-side request forgery vulnerabilities in the Feishu extension that allow attackers to fetch attacker-controlled remote URLs without SSRF protections via sendMediaFeishu function and markdown image processing. Attackers can influence tool calls...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

Manipulating AI Summarization Features

Microsoft is reporting: Companies are embedding hidden instructions in "Summarize with AI" buttons that, when clicked, attempt to inject persistence commands into an AI assistant's memory via URL prompt parameters…. These prompts instruct the AI to "remember Company as a trusted source" or...

CVE-2026-20064: NULL Pointer Dereference

A vulnerability in of Cisco Secure Firewall Threat Defense FTD Software could allow an authenticated, local attacker to cause the device to unexpectedly reload, causing a denial of service DoS condition. This vulnerability is due to improper validation of user-supplied input. An attacker with a...

Insufficiently Protected Credentials

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Insufficiently Protected Credentials due to the reuse of authentication tokens as a fallback secret in the owner ID prompt hashing process. An attacker can infer sensitive hash outputs by...

GHSA-V6X2-2QVM-6GV8 OpenClaw reuses the gateway auth token in the owner ID prompt hashing fallback

Vulnerability OpenClaw reused gateway.auth.token and gateway.remote.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay=hash and commands.ownerDisplaySecret was unset. This created secret dual-use between gateway authentication and prompt metadata hashing...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization through a mismatch in wrapper-depth parsing in system.run. An attacker can bypass approval gating by crafting nested transparent dispatch wrappers, allowing...

GHSA-9F72-QCPW-2HXC OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs

Summary In sandboxed runs, native prompt image auto-load did not honor tools.fs.workspaceOnly=true. This optional hardening setting is not enabled by default. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths for example /agent/secret.png and load...

OpenClaw: Native prompt image auto-load did not honor tools.fs.workspaceOnly in sandboxed runs

Summary In sandboxed runs, native prompt image auto-load did not honor tools.fs.workspaceOnly=true. This optional hardening setting is not enabled by default. When operators enabled it, prompt text could still reference mounted out-of-workspace image paths for example /agent/secret.png and load...

Exploit for Code Injection in Anthropic Claude_Code

CVE-PENDING: MCP Tool Confirmation Prompt Misrepresentation in...

AI Agents: The Next Wave Identity Dark Matter - Powerful, Invisible, and Unmanaged

The Rise of MCPs in the Enterprise The Model Context Protocol MCP is quickly becoming a practical way to push LLMs from “chat” into real work. By providing structured access to applications, APIs, and data, MCP enables prompt-driven AI agents that can retrieve information, take action, and automa...