Assess promptly

Cybersecurity researchers have discovered a set of trojanized npm packages that masquerade as working calendar and streak utilities but are engineered to stealthily deliver an artificial intelligence (AI)-powered Linux implant dubbed RedC2 4.0. "When the module loads, it locates the bundled binary, marks it executable, and launches it as a detached background process," TrendAI, Trend Micro's

Assess promptly

Researchers discovered a "meta-hacking" technique that can manipulate the AI service into revealing its own security weaknesses.

Assess promptly

New research shows how attackers can use security alerts and blocked events to manipulate and hijack AI agents.

Assess promptly

Attacker-controlled instructions can make Atlassian's Rovo assistant collect Jira or Confluence data that a signed-in user can access, then send it to an outside server. Two security firms found that behavior independently, by different routes. Only one of those routes is confirmed closed. PromptArmor, an AI security firm, hid the instructions in content Rovo reads. It said an uploaded file was

Program guidance

Google Cloud's Mandiant team published a practical model for using AI agents in vulnerability management without surrendering deterministic controls or human accountability.