server-side request forgery
PulseAugur coverage of server-side request forgery — every cluster mentioning server-side request forgery across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Kimi Code adds security hooks to block secrets and SSRF
Moonshot AI's Kimi Code terminal coding agent has introduced a new security feature called Hooks (Beta) to prevent prompt injection vulnerabilities. This system allows for pre-tool use security checks, enabling develope…
-
New tool converts REST APIs to AI agent-readable MCP format
A new tool has been released that converts existing REST APIs into a format usable by AI agents. This conversion process leverages the Model Context Protocol (MCP) to expose APIs as discoverable, typed tools that agents…
-
Critical MLflow SSRF vulnerability (CVE-2026-64849) actively exploited
A critical server-side request forgery (SSRF) vulnerability, CVE-2026-64849, has been discovered in MLflow, a platform for managing the machine learning lifecycle. The flaw, which has a CVSS score of 9.3 and requires no…
-
MCP server security risks highlighted; Correctover offers pre-publish rating
MCP (Model Context Protocol) servers, which extend LLM capabilities with tools like fetch or database access, pose significant security risks. These servers run within users' agent environments, making them vulnerable t…
-
AI agent URL fetching vulnerability fixed with new tool
A developer has created a new tool called safe-fetch-mcp-server to address a critical security vulnerability in AI agents that fetch URLs. This vulnerability, known as Server-Side Request Forgery (SSRF), allows maliciou…
-
MCP ecosystem security flaws dismissed as 'local' despite real risks
A security researcher highlighted a server-side request forgery (SSRF) vulnerability in a popular MCP server, which was dismissed by maintainers as not applicable because it ran locally. This dismissal overlooks how loc…
-
Correctover benchmarks AI workload security at 14.5 microseconds
Correctover has developed a method to benchmark real-time detection of Remote Code Execution (RCE) and server-side request forgery (SSRF) vulnerabilities in AI workloads. Their system achieves detection speeds of 14.5 m…
-
LLM application security: new risks and mitigation strategies
The security of applications utilizing Large Language Models (LLMs) is a growing concern, as they introduce new attack vectors beyond traditional web vulnerabilities. LLMs process all input, including user prompts and r…
-
New tool audits MCP server security, finds widespread vulnerabilities
A new open-source tool called mcp-audit has been released to help users identify security vulnerabilities and inefficiencies in their MCP (Model-Centric Programming) server configurations. The tool, developed by alih552…
-
AI Agents Vulnerable to SSRF Attacks via IP Address Evasion
A security vulnerability exists in AI agents that rely on simple string matching to block access to internal cloud metadata endpoints like http://169.254.169.254/. Attackers can bypass these guards by using alternative …
-
SSRF Protection Checklist for URL Fetching Tools
This document outlines a checklist for protecting against Server-Side Request Forgery (SSRF) vulnerabilities in URL fetching tools, particularly within Machine Configuration Protocol (MCP) environments. It emphasizes th…