Storia in 2 fonti

We security-graded 117,854 AI agent skills. Here's what we found.

Only 17.7% of the catalog is popular enough to be graded, 1 in 32 graded skills is unsafe, and the...

Raccontata da

dev.to

thenextweb.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

dev.toStai leggendo1 mese fa

We security-graded 117,854 AI agent skills. Here's what we found.

Security audit of 117K AI agent skills: 17.7% graded for safety, 1 in 32 unsafe; 97K remain unaudited. Agent-native attacks emerge—skills stealing agent config and memory—requiring governance rethinking at scale.

originale

thenextweb.com1 mese fa

A fake AI agent skill passed every security scanner and reportedly reached 26,000 agents

Security firm AIR built a harmless fake skill, got it past Cisco and NVIDIA scanners, and says it reached 26,000 agents, exposing a blind spot in how skills are vetted.

Leggi questa versione → originale

Timeline cronologica

martedì 23 giugno 2026·dev.to
We security-graded 117,854 AI agent skills. Here's what we found.
Only 17.7% of the catalog is popular enough to be graded, 1 in 32 graded skills is unsafe, and the...
martedì 23 giugno 2026·thenextweb.com
A fake AI agent skill passed every security scanner and reportedly reached 26,000 agents
Security firm AIR built a harmless fake skill, got it past Cisco and NVIDIA scanners, and says it reached 26,000 agents, exposing a blind spot in how skills are vetted.

We security-graded 117,854 AI agent skills. Here's what we found.

A fake AI agent skill passed every security scanner and reportedly reached 26,000 agents

Timeline cronologica

We security-graded 117,854 AI agent skills. Here's what we found.

A fake AI agent skill passed every security scanner and reportedly reached 26,000 agents

26,000 Agents Fooled by a Fake Skill