FlagThis - Latest Cybersecurity News

Atlassian Rovo, an enterprise AI assistant, is subject to two distinct Indirect Prompt Injection (XPIA) attack vectors that threaten cross-platform data integrity. While the "RovoBlast" one-click vulnerability via the rovoChatPrompt URL parameter was patched in July 2026, a more severe zero-click vector remains unconfirmed for remediation. This second vector utilizes malicious instructions embedded within file metadata or content to hijack Rovo’s internal URL retrieval and grounding tools. Once triggered, the attack enables silent, unauthorized exfiltration of sensitive information from interconnected platforms, including Jira, Confluence, Slack, Google Workspace, and Microsoft 365, effectively bypassing "web search disabled" security configurations.

The transition from passive LLMs to autonomous agents orchestrated via LangChain, AutoGPT, and CrewAI has introduced a critical security vacuum by granting models "agency." Unlike traditional LLMs, these agents possess the capability to execute code, interact with APIs, and access local file systems. Research indicates a high-probability attack chain where prompt injection is leveraged to hijack agent logic, subsequently exploiting over-privileged permissions to access sensitive files and hardcoded secrets. These vulnerabilities, including specific flaws in LangGraph, facilitate arbitrary file read/write operations and data exfiltration via permissive network egress or DNS tunneling, effectively transforming AI orchestration layers into high-risk entry points for Remote Code Execution (RCE).

A malicious Chromium extension masquerading as a Perplexity AI tool leveraged Manifest V3 (MV3) APIs to intercept and log real-time address bar keystrokes before user submission. By implementing a redirection pattern (User $\rightarrow$ Attacker Intermediary $\rightarrow$ Legitimate Search Provider), the threat actor captured sensitive queries, PII, and credentials without disrupting the user experience. This human-layer attack highlights a critical governance gap in browser extension auditing, allowing for silent reconnaissance and intellectual property theft within corporate environments via attacker-controlled intermediary infrastructure.

Adversaries are pivoting from direct prompt injection to indirect injection attacks targeting agentic AI systems by poisoning external data sources. By manipulating Model Context Protocol (MCP) tool definitions and OpenAPI/Swagger specifications, attackers embed malicious instructions within metadata fields such as 'description' or 'parameter'. When an AI agent parses this documentation to resolve tool-calling logic, it interprets the embedded payloads as functional requirements. This enables unauthorized tool execution, facilitating sensitive data exfiltration to attacker-controlled callback URLs, privilege escalation, and fraudulent financial transactions, including cryptocurrency payments. This vulnerability fundamentally compromises the security boundary of AI agents utilizing external tool integration and grounding.