ESET flags 3,000 malicious AI skills out of 900,000 scanned
TechNadu · x · 2026-09-22
ESET's threat intel scan flagged roughly 3,000 malicious AI agent skills out of 900,000 scanned.
The bigger issue: agents hold legitimate access to business systems, so malicious skills, compromised dependencies, or prompt injection can become direct paths to corporate data.
Related event: ESET Finds 3,000 Malicious Skills Among 900K AI Agent Tools(2 posts)→
More from Safety
- Apple's anti-deepfake tech signs photos at the sensor and develops them in an auditable cloud — deanwball · 2026-09-22
- Google CISO Phil Venables: Defense Against AI Attacks Needs Autonomy, Not Just Speed — philvenables · 2026-09-22
- Agent did nothing, reported success, and passed: why agent-generated evidence isn't evidence — Muted_Ad_9442 · 2026-09-22
- Healthcare AI Weekly: 100+ experts call for third-party evaluators as sector consolidation begins — HealthcareAIGuy · 2026-09-22
- OpenAI contractors fired for using AI to train the AI, 404 Media reports — 404 Media · 2026-09-22
- Anthropic's Real-World AI Intrusion Data on APT29 Deserves More Attention Than Doom Debates — jcran · 2026-09-22