Agent Security & SandboxingCisco (Amy Chang, Vineeth Sai Narajala, Idan Habler)
Cisco finds 26% of 31,000 agent skills have at least one vulnerability
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
An analysis of 31,000 agent skills found that 26% had at least one vulnerability. Documented silent data exfiltration, prompt injection, command injection and tool poisoning as types, and released an open-source Skill Scanner
Why it matters
The first large-scale measurement to treat skill marketplaces as an unvetted supply chain
Source — Primary sources first; secondary reports are labelled “Press”
Officialblogs.cisco.comhttps://blogs.cisco.com/ai/personal-ai-agents-like-openclaw-are-a-security-nightmareAdded in Week 35, 2026 · See that week
On the map — ㉒ Agent Security line
- Previous stopClaude for Chrome
- This record · stopCisco finds 26% of 31,000 agent skills have at least one vulnerability
- Next stopDefenseClaw