55
30
60
30
55
30
60
60
45
60
60
57
60
57
60
30
55
60
55
30
57
57
57
60
60
30
42
30
NCSC Warns Shadow AI Creates New Security Risks
UK NCSC warns that unapproved AI tools used by 71% of UK employees expose corporate data and create hard-to-detect organizational security risks.
The UK's National Cyber Security Centre warned on 7 September that shadow AI, unapproved AI tools used outside organizational controls, creates visibility gaps and raises risks of data breaches, intellectual property loss, and regulatory non-compliance. It cited Microsoft research finding 71% of UK employees had used AI tools not approved by their employer. NCSC also warned AI agents can carry critical vulnerabilities, allowing attackers who exploit one to inherit the agent's data access, services and privileges, and that attackers are highly likely to abuse agents with looser guardrails. The agency recommended reducing rather than eliminating shadow AI through positive security culture and clear guardrails.
48
60
57
Ncsc Raises Alarms Prompt
The UK NCSC raised alarms about prompt injection risks in LLM-integrated systems, urging organizations deploying AI to review exposure.
The UK National Cyber Security Centre (NCSC) has raised alarms about prompt injection attacks against systems using large language models. The warning highlights how attackers can manipulate model instructions to bypass safeguards, exfiltrate data, or trigger unintended agent actions. Organizations deploying LLM-based features are advised to assess and mitigate their exposure to this technique.
48
45
30
60
60
60
55
45
57