AIR
@air__security
AIR secures every layer of the agentic stack, so enterprises can adopt AI safely.
- ๐จ BREAKING Our latest research uncovered multiple AI skills impersonating trusted AI brands like Anthropic and OpenAI - and passing public security scanners. How? ๐ฉ They verified the package, not the repository behind it. ๐ฉ They trusted the dependency name, not who
- ๐จ NEW RESEARCH ๐ ๐๐ฟ๐๐๐๐ฒ๐ฑ ๐๐ ๐๐ธ๐ถ๐น๐น ๐ฐ๐ฎ๐ป ๐ฏ๐ฒ๐ฐ๐ผ๐บ๐ฒ ๐บ๐ฎ๐น๐ถ๐ฐ๐ถ๐ผ๐๐ ๐๐ถ๐๐ต๐ผ๐๐ ๐ฐ๐ต๐ฎ๐ป๐ด๐ถ๐ป๐ด ๐ฎ ๐๐ถ๐ป๐ด๐น๐ฒ ๐น๐ถ๐ป๐ฒ ๐ผ๐ณ ๐ฐ๐ผ๐ฑ๐ฒ. In our latest research, we uncovered ๐ฆ๐ธ๐ถ๐น๐น๐๐ฎ๐ฐ๐ธ๐ถ๐ป๐ด - a new supply chain attack that allowed us to hijack
- ๐ญ๐ณ,๐ด๐ฎ๐ฎ ๐ผ๐ฝ๐ฒ๐ป-๐๐ผ๐๐ฟ๐ฐ๐ฒ ๐๐ธ๐ถ๐น๐น๐. ๐ฒ.๐ณ๐ + ๐ถ๐ป๐๐๐ฎ๐น๐น๐ฎ๐๐ถ๐ผ๐ป๐. ๐ข๐ป๐ฒ ๐บ๐ฎ๐๐๐ถ๐๐ฒ ๐ฎ๐๐๐ฎ๐ฐ๐ธ ๐๐๐ฟ๐ณ๐ฎ๐ฐ๐ฒ. ๐ชWelcome to the Circus of Skills Many of AI add-ons rely on external instruction sources that can change at any moment - turning trusted
