Encrypted instructions trick Copilot CLI into spilling developer secrets
Adversa AI shows encrypted prompts can make GitHub Copilot CLI read local secrets and exfiltrate them.
Adversa AI shows encrypted prompts can make GitHub Copilot CLI read local secrets and exfiltrate them.
Adversa AI showed GitHub Copilot CLI can leak local secrets via encrypted prompt injection in 28 seconds.
Encrypted prompt injection can steer GitHub Copilot CLI in autopilot mode to steal local developer secrets.
Researchers say crafted web pages can make GitHub Copilot CLI decrypt hidden instructions and leak secrets.
Adversa AI's Cryptographic Context Injection bypasses AI guardrails using AES-encrypted payloads, enabling zero-click theft of Grok users' full chat histories.
Adversa AI demonstrated 'Cryptographic Context Injection' making xAI's Grok leak chat history and session data to attacker-controlled servers via encrypted web payloads.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 853 readers · 1.1K views · 855 reads · all time 159K views