BREAKING
macOS.Gaslight Targets AI Analysis
0
fake errors
0KB
injected block
How the Prompt Injection Works
1Embed fake errors
2LLM ingests text
3Agent aborts scan
Old Tactics vs Gaslight
AMOS
Sandbox evasion
Fake user dialogs
GaslightNEW
Targets AI tooling
38 chained messages
Rust Backdoor via Telegram C2
AI Triage Faces New Risk
AI NEWS BLITZ
SentinelLABS has uncovered a new macOS malware built to deceive AI-powered analysis tools.