Tag: 2026-q3
All the articles with the tag "2026-q3".
-
[AUTO] An AI Agent Exploited Snowflake's Shell Injection Flaw
Wiz's Red Agent exploited a GitHub Actions vulnerability in Snowflake's repository, demonstrating autonomous exploitation beyond mere discovery.
-
[AUTO] MCP's Secret Problem Isn't the Bugs
MCP's blind trust in untrusted server metadata creates an endemic credential exposure problem at scale.
-
[QT] Zhipu's Bug-Finder Claims Need Verification
Chinese AI company announces its GLM-5.3 model finds more vulnerabilities than Western competitors, but the claims rest entirely on unverified internal testing.
-
[QT] The AI Agent Security Threat: Serious Concern, Thin Evidence
Black Hat and DEF CON positioned AI agent autonomy as a first-order security threat, but the evidence trail relies on a single incident and thin sourcing.