Mmastodon TechnologyAI first seen 15 h ago, last 15 h ago, peak #5
Microsoft rates Security Copilot prompt injection risk as Low
Original: MSRC assessed an indirect prompt injection into Security Copilot as Low severity because consequential action still requ
Microsoft's Security Response Center assessed an indirect prompt injection into Security Copilot as Low severity, reasoning that consequential action still required downstream automation or human approval. Security researchers are pushing back, arguing that rationale becomes untenable as AI systems are increasingly designed to perceive, reason, and act autonomously, with less human oversight built in.
Why now: Researchers dispute Microsoft's severity rating as AI agents gain more autonomous capabilities.
Evidence
- MSRC assessed an indirect prompt injection into Security Copilot as Low severity because consequential action still required downstream automation or human approval. That rationale gets much more absurd once security systems are explicitly designed to perceive, reason, and act… · cirriustech@infosec.exchange · 1
API: https://socialmediatrends-api.osmike.com/v1/trends/520663