PulseAugur
EN
LIVE 01:20:32
ENTITY Pillar Security

Pillar Security

PulseAugur coverage of Pillar Security — every cluster mentioning Pillar Security across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
5
6 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
0 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

4 day(s) with sentiment data

RECENT · PAGE 1/1 · 7 TOTAL
  1. TOOL · CL_346323 ·

    Critical vulnerability in MCP Inspector allows remote code execution on Windows

    A critical vulnerability, CVE-2026-119025, has been discovered in the MCP Inspector, a tool used to test remote Model Context Protocol servers. The vulnerability allows a malicious MCP server to execute arbitrary PowerS…

  2. TOOL · CL_333394 ·

    New tool sandfit simplifies AI coding agent sandbox security

    A new tool called sandfit aims to address the challenge of configuring secure sandboxes for AI coding agents. Many users disable these sandboxes due to the difficulty of creating an initial allowlist of necessary permis…

  3. TOOL · CL_331415 ·

    AI Coding Agent OpenCode Vulnerable to Command Execution via MCP Servers

    A vulnerability in OpenCode, an AI coding agent, allowed untrusted MCP servers to execute commands on developer machines via a malicious OAuth sign-in process. This issue, reported by Pillar Security and affecting versi…

  4. TOOL · CL_324134 ·

    MCP Server Audit Logging Guide Details Deadbugz Attack Response

    This guide outlines essential logging practices for detecting and investigating attacks on MCP servers, particularly in the context of the Deadbugz campaign. It emphasizes the need to log not only tool calls but also to…

  5. TOOL · CL_278124 ·

    AI Agent Supply Chains Riddled with Silent Malware, Researchers Warn

    A recent analysis of AI agent supply chains reveals widespread vulnerabilities, with malicious actors exploiting official MCP servers and GitHub pull requests to distribute malware. Researchers found that these maliciou…

  6. TOOL · CL_185550 ·

    Google ADK vulnerability allows AI agents to trigger privileged workflows

    Pillar Security has identified a vulnerability within Google's ADK system. This flaw allows for prompt injection attacks, enabling low-privilege AI agents to execute privileged CI/CD workflows. The discovery highlights …

  7. TOOL · CL_10927 ·

    Google's Gemini CLI fix creates new CI/CD pipeline issues

    Google has patched a critical vulnerability in its Gemini command-line interface (CLI) tool that could allow for remote code execution. The flaw, which had a CVSS score of 10.0, stemmed from the tool's automatic trust s…