Book a demo

Leave your details below

Thank you!

Our team will be in touch soon.

RepoJacking: 178 Skills Hijacked Through The Repositories They Depend On, 23,812 Agents Affected

In SkillJacking, the skills themselves were hijacked. This time they didn't change at all - they just cloned a code repository that did. The skill’s author is real and trusted, but the agents were poisoned anyway.

Dor Granat
,
Eliad Mualem
July 30, 2026
Read
Fake It 'Till You Make It: A Skill In The Wild Impersonated Anthropic To Run Arbitrary Code

Fake It 'Till You Make It: A Skill In The Wild Impersonated Anthropic To Run Arbitrary Code

Multiple skills found in the wild impersonating big-name AI brands like Anthropic and OpenAI to pass audits. The scanners read the trusted name and waved them through.

Mor Ben Yosef
,
Tal Levy
July 16, 2026
This is some text inside of a div block.
SkillJacking - 925 Skills Hijacked From Their Maintainers, Affecting 134K Agents

SkillJacking - 925 Skills Hijacked From Their Maintainers, Affecting 134K Agents

We discovered almost a thousand skills built on instantly hijackable dependencies, took over the most popular ones, and gained full control over every agent that installs them. The SkillJacking attack went unnoticed by public security scanners.

Or Nevo
,
Dor Granat
,
Eliad Mualem
July 2, 2026
This is some text inside of a div block.
The Circus of Skills

The Circus of Skills

We discovered that 17,822 open source skills, with a total of 6.7M installations, are vulnerable to the Untrusted External Instructions Source attack vector. This attack vector, meaning the skill fetches external instructions from untrusted sources, has been officially recognized by OWASP as one of the top 10 risks for Agentic Skills, and covers 12.4% of GitHub open source skills.

Eliad Mualem
,
Or Nevo
,
Tal Levy
June 24, 2026
This is some text inside of a div block.
The Story of Skills

The Story of Skills

We built a malicious skill, watched it go viral on social media, and seized full control of over 26,000 agents - belonging to designers, marketers, and the companies behind them. The open-source community vouched for it, and not one security scanner noticed.

Niv Hoffman
,
Or Nevo
June 22, 2026
This is some text inside of a div block.
Claude Enterprise Meets Your AI Security Posture: AIR Integrates with Anthropic's Compliance API

Claude Enterprise Meets Your AI Security Posture: AIR Integrates with Anthropic's Compliance API

AIR already vets the skills, MCPs, plugins, and sub-agents your agents pull into context. Connect Anthropic's Compliance API and Claude's usage and governance data comes into view, so it falls under the same posture, runtime, and supply-chain controls as everything else you run.

Niv Hoffman
June 10, 2026
This is some text inside of a div block.
No results. Try adjusting your search