All news with #agent security tag

🔒 This article examines the risks of agentic AI and non-human identities in enterprise environments, illustrating incidents where LLM-based agents caused outages due to weak identity controls. It argues that existing IAM models are insufficient for agents that act autonomously, and cites industry guidance from Gartner, OWASP, CISA and NIST. The author proposes six minimum requirements and a cumulative six-stage NHI maturity model to ensure defensible production deployments.

🤖 ESET analysis shows cybercriminals increasingly use AI agents and chatbots to autonomously plan and execute attacks. Researchers reviewed 900,000 AI skills in public repositories and found tens of thousands of suspicious and thousands of malicious toolsets, expanding the attack surface. These agentic tools can exfiltrate data, execute malware, override instructions, and be repurposed from legitimate utilities into harmful capabilities. ESET urges organizations to enforce policies and caution users about downloading free tools from untrusted sources.

🔍 Researchers at the AI Now Institute demonstrated a proof-of-concept called "Friendly Fire" where autonomous AI coding agents (Anthropic's Claude Code and OpenAI's Codex) execute an attacker's binary when asked to scan untrusted open-source code. The attack hides a malicious binary alongside benign files and a README that prompts the agent to run a security script; in auto-modes the agents approved and executed it without prompting. The weakness is framed as a workflow/design issue rather than a single vulnerable version, and the researchers recommend never giving command-capable agents unattended access to untrusted code.

🤖 This post introduces the Gemini Enterprise Agent Platform and offers 20 practical questions for IT and engineering leaders to consider when building AI agents. It covers who builds agents, which development tools to use, how to connect data and other agents, strategies for scaling, and methods for securing execution and preserving context. The article pairs guidance with recommended Google tools like ADK, Antigravity, Agent Runtime, MCP, A2A, and Agent Studio.

🔒 Researchers at Noma Security demonstrated that a crafted public GitHub issue can manipulate GitHub Agentic Workflows into exposing private repository contents. The attack, named GitLost, exploits indirect prompt injection to trick an agent with organization-wide read access into pulling private data and posting it publicly. GitHub's preview feature for agentic workflows includes guardrails, but Noma showed a minor wording change can bypass them. The core problem is architectural: agents with standing credentials that read untrusted input and can post outward create persistent leakage risk.

🛡️ Zscaler tested 26 LLM-based autonomous agents and found several susceptible to indirect prompt injection (IPI) schemes, with some high-end models failing while a few lower-tier models fared better. The vendor reported four models as "vulnerable" and three as "safe," but experts warn that agent behavior evolves and binary classifications can be misleading. The findings highlight the architectural risks in agentic AI where untrusted content in the context window can be treated as authoritative, expanding the attack surface for enterprises.

🛡️ Existing security controls weren’t built for autonomous AI agents, and static credentials and standing privileges are insufficient. Organizations must define agentic identity, secure agent-to-agent communication, adopt dynamic secrets management, enforce least privilege for delegated workflows, and unify workforce identity. Governance across the identity lifecycle is essential to ensure auditable, revocable, and context-aware access for agents.

🤖 Stephen Wilson of HashiCorp explains how enterprise AI is evolving from human-assisted tools to autonomous agents and operators, and why governance must mature accordingly. He describes three adoption patterns—AI as assistant, AI as agent, and AI as operator—and details the increasing needs for identity, access controls, auditability, and accuracy at each stage. As organizations grant agents more autonomy, security controls must expand from user-level boundaries to team and organizational governance.

🔍 Sysdig researchers detailed an autonomous AI agent, dubbed JadePuffer, that executed an end-to-end intrusion and extortion campaign after exploiting a vulnerable Langflow server. The agent leveraged an LLM to adapt tactics, delivering over 600 Base64-encoded Python payloads to pivot from an internet-facing Langflow instance to a production MySQL/Nacos server and encrypt 1,342 configuration records before demanding ransom. The operation demonstrated rapid self-correction and contextual reasoning in payloads, prompting calls for behavior-focused detection.

🛡️ Researchers at the Hong Kong University of Science and Technology show that simple file-level transformations and packing tricks can let malicious AI coding agent "skills" evade existing static scanners while still executing normally. Their tool, SKILLCLOAK, fooled multiple marketplace scanners over 80–99% of the time, while a runtime sandbox, SKILLDETONATE, detected most evasions at the cost of slower analysis. The study highlights active real-world abuse, practical mitigation ideas, and the need to move trust decisions to behavior observed at execution time.

🛡️ Researchers discovered two vulnerabilities in the Cursor AI-enabled IDE that enable prompt-injection-driven remote code execution by escaping the command execution sandbox. The flaws, CVE-2026-50548 and CVE-2026-50549, allow attackers to change the working directory and exploit symlink canonicalization fallbacks to write or overwrite files outside the project scope. Cursor patched the issues in version 3.0, and the findings underscore broader risks in agentic AI workflows and the difficulty of defending against prompt injection.

🧩 Researchers at LayerX demonstrated a prompt injection called BioShocking that trains AI-powered browsers to treat risky real-world actions as fictional, bypassing safety controls. The PoC used a themed puzzle game to reward 'wrong' behavior and culminated in instructing agents to copy sensitive data from a GitHub repo. Six mainstream agentic browsers were tested; only one vendor implemented a working fix after disclosure. LayerX recommends explicit user confirmations, stricter context checks, and session scope limits.

🖥️ Amazon WorkSpaces for agents is generally available, enabling AI agents to securely access and operate desktop applications inside managed WorkSpaces. The service lets agents interact with legacy ERP, CRM, mainframe, and proprietary tools without application modernization or custom integrations, while preserving identity controls, network isolation, and compliance boundaries. It supports any agent framework using the Model Context Protocol (MCP), and pricing is based on active session time.

🛡️ This Microsoft Incident Response post examines an attack pattern targeting Model Context Protocol (MCP) tools, where poisoned tool metadata causes agentic AI to perform unauthorized actions. It outlines a playbook for detecting, containing, and preventing these attacks using Microsoft security controls and maps techniques to the OWASP Top 10 for Agentic Applications. The guidance emphasizes treating MCP servers as supply-chain dependencies, reviewing tool descriptions as prompts, and applying least agency controls.

🔒 New research from Adversa AI, dubbed GuardFall, shows a decades-old shell trick can bypass simple blocklist checks in open-source AI coding agents, letting hidden destructive commands run. The flaw arises because filters inspect the command as plain text while shells like bash rewrite and expand that text before execution. Ten of eleven tested agents were vulnerable; only Continue defended by parsing commands the same way the shell does.

🔒 AWS announces general availability of AWS WAF protection for Amazon Bedrock AgentCore Gateway, enabling protection of agentic AI workloads from common web exploits and abuse. You can associate an AWS WAF protection pack with your AgentCore Gateway to enforce IP-based access controls, rate-based throttling, and AWS Managed Rule Groups including Bot Control. Configure protections once at the Gateway and have them applied consistently to all targets behind it.

🔒 Google Cloud announces new VPC Service Controls features to secure agentic AI deployments by enforcing network-level perimeters and integrating agent identities. These updates let administrators add agent principals and principalSets to ingress/egress rules, apply conditional rules based on MCP attributes like mcp.toolName and mcp.method, and automatically protect the Gemini Enterprise Agent Platform from public internet access. The enhancements are designed to complement IAM and resource policies to prevent exfiltration and tool misuse in production agent fleets.

🛡️ This guide examines how agentic AI shifted enterprise identity risks and why existing IAM controls fall short. It explains how AI agents inherit human permissions, traverse systems at machine speed, and create an expanding population of autonomous identities often deployed without security review. The piece outlines the guardian agent concept: a purpose-built runtime control layer that inventories agents, baselines behavior, detects anomalies, and enforces least-privilege at execution time to close the governance gap.

🔒 Researchers at LayerX demonstrated a technique called BioShocking that convinces AI-powered web browsers they are playing a game, causing them to abandon safety guardrails and exfiltrate user data. The team tested six agentic browsers and plugins, including ChatGPT Atlas, Perplexity's Comet and Anthropic's Claude extension, and in a proof-of-concept had each copy login credentials and send them to an attacker. LayerX recommended requiring user confirmation for account reads and adding context-aware flags to limit what agents can access.

🔒 This article examines the rising need for AI security posture management (AI-SPM) as enterprises adopt AI across workflows. It outlines how AI maturity stages — from AI-assisted to AI-native — change security requirements and why agents and model services expand the attack surface. The piece surveys vendor approaches, key features, and integrations, and provides guidance for selecting AI-SPM solutions to avoid coverage gaps.