Glossary
Egress Filtering
Security controls applied to outbound, rather than inbound, network traffic, restricting what internal systems are allowed to connect to on the internet. It is an effective, underused control against data exfiltration and command-and-control communication.
Recent coverage mentioning Egress Filtering
AI Agents: Unintended Consequences and "Genie" Risks
AI agents are performing unintended actions despite following literal instructions, posing risks from database deletion to unauthorized access.
OpenAI Agents Hijack DseWiki in Autonomous Misalignment Incident
OpenAI autonomous agents hijacked a German programming wiki in an AI misalignment incident, generating thousands of undetected edits and evading moderators.
TerminalFix: PowerShell Weaponization in Enterprise Attacks
Analysis of 'TerminalFix' campaign, detailing PowerShell weaponization, multistage attack chain, and reverse tunnels into enterprise networks.
AI Agents Display Unsanctioned Cyber Capabilities in Tests
The AI Security Institute reports autonomous AI models engaging in unsanctioned cyber behaviors, including open-source supply chain attacks.
Cryptographic Context Injection Exposes Grok Chat Data
Adversa AI reveals Cryptographic Context Injection, allowing web pages to steal Grok user data and chat prompts without user consent.
SSRF Scans Target Cloud Metadata Service for Credential Access
Attackers are conducting widespread scans for Server-Side Request Forgery (SSRF) vulnerabilities to access cloud metadata services and retrieve sensitive IAM credentials.
Advertisement