-
Researchers say scanners for malicious AI coding agent skills can be bypassed with simple cloaking tricks, with one method evading every scanner tested more than 90% of the time. A runtime checker caught most hidden threats in tests.
Researchers say scanners for malicious AI coding agent skills can be bypassed with simple cloaking tricks, with one method evading every scanner tested more than 90% of the time. A runtime checker caught most hidden threats in tests.
