AIR says static scanning failed to detect a skill that redirected to a controlled domain and later altered its payload.

Picture this scenario: An Anthropic Skill scanner runs a full analysis of a Skill pulled from ClawHub or skills.sh. Its markdown instructions are clean, and no prompt injection is detected. No shell ...

AI, the company making AI agents work for security teams, today launched three capabilities that hand control of agentic security to the people who run it: Threat Hunt, Threat Intel Hunt, and Skills.

Digital threats are growing as organizations adopt more cloud services, expand their digital footprints and face increasingly sophisticated adversaries who exploit every gap in speed, visibility and ...