Tag
#ai-agent-security
AgentsJul 13, 20264 min read
OpenAI's Safe Url Defense Targets Agent Prompt Injection
OpenAI details how ChatGPT agents resist prompt injection: a Safe Url check blocks data leaks after a compliance-email scam worked half the time in testing.
AgentsJul 13, 20266 min read
SkillCloak Bypasses AI Agent Skill Scanners 90% of the Time
HKUST researchers tested SkillCloak on eight scanners and 1,613 real malicious skills from ClawHub — every one fell, with evasion above 90%, up to 99%.
Dev ToolsJul 13, 20267 min read
MCP Gateway Buyer's Checklist: SSO, SCIM, RBAC, and Audit Logs
MCP adoption has reportedly crossed 78%, yet most gateways still lack SSO, SCIM provisioning, audit trails, and per-action RBAC enterprises require.