Inmate Used Prompt Injection to Get AI to Write Exploit Code

While awaiting sentencing for the AT&T/Verizon telecom extortion scheme, U.S. Army soldier Cameron Wagenius used other inmates' email accounts to prompt a commercial AI tool for Windows and D-Link CVE exploit code and prison-escape/antenna-building information, disguising the requests as research for a book to evade the tool's safety restrictions.

Occurred 1 September 2025 · Disclosed 19 September 2026 · Record updated 1 October 2026

Impact

Bureau of Prisons flagged the inmate's attempts to obtain real-world exploit code and prison escape information via AI prompts routed through other inmates' email accounts; no confirmed successful exploitation resulted.

Our coverage

A caged figure whispers coded riddles through prison bars to a glowing machine outside, which obeys the hidden instructions and spits out forbidden blueprints.

Incidents

Prosecutors say jailed hacker used AI jailbreak to seek exploit code

A US soldier sentenced over the AT&T and Verizon extortions asked other inmates to feed disguised prompts to a commercial AI tool, according to a government filing.

25 Sept 2026

Sources

krebsonsecurity.comhttps://krebsonsecurity.com/2026/09/u-s-soldier-gets-70-months-in-prison-for-att-verizon-extortions