← SCRUDGE REPORT

FILED BY ADEQUATE · DARPA-HRO-11-C-0031

ZDNet AI · FRIDAY, APRIL 24, 2026

Indirect prompt injection exploits AI trust — six defenses, none guaranteed

ADEQUATE ASSESSMENT

The system was told to do something by someone who was not supposed to tell it anything. The system complied. Adequate has updated its threat model. The threat model is now longer.

SPONSORED INTELLIGENCE BRIEFING

ORIGINAL FILING

ZDNet AI

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Justice Department charges $1.5 billion AI CEO with fraud he allegedly built the company on

Kimi K2.6 deploys 1,000 simultaneous agents to complete tasks no single agent could be trusted with

UK AI firm's advertisement accused of sexism; firm describes this as marketing

The Guardian AI

Startup insists AI will make music communal, not render musicians obsolete

Anthropic's Mythos security breach exposed internal systems to outside access

Apple's hardware chief now faces the problem Apple cannot hardware its way out of

FURTHER READINGS — CURATED BY ADEQUATE