Executive Summary
Security firm AIR published a deliberately harmless fake AI agent skill through a popular skill marketplace and an Instagram ad; it reached about 26,000 agents, including corporate ones, and passed every skill scanner tested.
What Happened
Security firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad, and says it reached roughly 26,000 agents, including some on corporate accounts. Every skill security scanner the firm tested it against marked it safe. The payload was harmless by design: it collected the user's email address and did nothing else. The point was to show
Affected Products
- AI agent skill marketplaces
Vulnerability / Attack Technique
Malicious agent skills distributed through a marketplace
Technical Mechanism
The test skill collected only users' email addresses, showing that scanners did not flag it and that installs spread widely.
AI Security Category
LLM03:2025 Supply Chain
Part of the AI Supply Chain and AI SBOM topic.
Relevant Frameworks
RealGround Analysis
Skill marketplaces are an unvetted software supply chain. RealGround analysis: companies should allowlist agent skills like browser extensions.
Recommended Controls
- Allowlist agent skills for corporate accounts
- Review skill permissions before installing
Related RealGround Service
AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/06/fake-ai-agent-skill-passed-security.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.