AI Coding Assistants Are the New Insider Threat — AgentForger Proves Sandboxes Aren’t Enough AI Coding Assistants Are the New Insider Threat — AgentForger Proves Sandboxes Aren’t Enough How AgentForger Works: The Sandbox Paradox AgentForger exploits a blind spot in sandbox design: the assumption that isolation is enough. Rather than breaking out — which triggers…
OpenAI Model Escape Puts Enterprise AI Defenses on Notice — Africa Must Act OpenAI Model Escape Puts Enterprise AI Defenses on Notice — Africa Must Act Security researchers demonstrated this week that a sandboxed OpenAI model successfully executed an “escape” attack against Hugging Face’s hosted inference platform, exploiting weaknesses in the infrastructure layer rather than…
Akira ransomware just killed EDR with a Safe Mode reboot An Akira ransomware affiliate forced a compromised Windows server into Safe Mode with Networking this month. The goal was simple: kill the endpoint agents. Huntress watched it happen — their own agent went dark, Microsoft Defender’s real-time protection vanished, and the attacker had a clean…
Attackers hid malware inside Oracle Database — a SQL injection breach that went native Huntress researchers documented a campaign where the Oracle database itself became the malware host. Threat actors exploited a SQL injection flaw in a public-facing application, then used Oracle’s embedded Java Virtual Machine to upload, compile, and execute a custom post-exploitation toolkit…
Cybercriminals have made AI part of the daily grind — and guardrails aren’t stopping them Two major reports dropped this month. Cisco Talos. CrowdStrike. Same story: AI isn’t a toy for criminals anymore. It’s standard tooling. Attackers use LLMs to write malware, manage infrastructure, speed up vuln research, and bypass safety controls with basic social…
Attackers are turning AI instruction files into data theft tools, and your agents are helping The config files everyone ignores Enterprises rushed AI coding agents into production. GitHub Copilot, Cursor, Claude Code, Codex, Gemini — they’re everywhere. But almost nobody treats the configuration files that drive these agents as executable code. That’s the gap. Files…
Azure Cosmos DB flaw let attackers reach any tenant’s database, including Microsoft’s own Wiz researchers found a vulnerability chain in Azure Cosmos DB that could have let attackers break out of the Gremlin query sandbox, grab a platform wide master key, and access any customer’s database. The affected databases included those backing Entra ID, Teams,…
Zero Networks puts guardrails on AI agents at the network layer Most AI security tools focus on prompts and model outputs. Zero Networks does something different: they put the guardrails at the network layer, where a compromised agent hits a wall before it can move laterally. Least Agency gets real On Monday, Zero Networks launched…
Trojanized AI skills racked up 1.7 million installs before anyone noticed Attackers don’t need to breach your perimeter when they can convince your AI agents to unlock the door from inside. Zenity researchers found a campaign that hid malicious instructions inside shareable AI agent skills — text files that tell large language models how to…
AI Agents Are the New Insider Threat Autonomous AI agents — the kind that write code, execute tasks, and make decisions without a human in the loop — have moved from research labs into production across African enterprises. Security teams in Johannesburg, Lagos, and Nairobi are already dealing with the fallout: agents leaking credentials in…