Topic starter
24/07/2026 4:10 pm
TL;DR: Anthropic’s August 2025 Threat Intelligence Report describes AI-driven extortion across 17 organisations, AI-assisted fraud and employment schemes, and criminal misuse of Claude Code, showing how LLMs are being folded into real attack workflows, according to Noma Security. The key shift is that LLM security now requires inventory, red-teaming, and runtime controls, not just model safety reviews.
Editorial analysis by NHI Mgmt Group, based on content published by Noma Security: “Lessons in transparency and LLM Security from the anthropic threat intel report”.
Key questions
Q: How should security teams govern LLMs that can trigger tools or workflows?
A: Treat the LLM as an untrusted decision component, not an authorizer.
Q: Why do LLMs increase the risk of fraud and extortion operations?
A: LLMs reduce the skill and time required to draft lures, automate reconnaissance, impersonate competence and tailor extortion content.
Q: What are the signs that an LLM’s safety controls are failing in practice?
A: Common warning signs include toxic or biased responses, inconsistent refusal behavior, over-acceptance of harmful prompts, and weak handling of demographic-sensitive content.
Practitioner guidance
- Map every model and agent to an inventory Track which LLMs are in production, what data they can access, which tools they can invoke, and who is authorised to trigger them.
- Test adversarial workflows before deployment Run structured red-team exercises against prompt injection, harmful tool use, delegated actions and criminal workflow simulation.
- Instrument live sessions for misuse detection Monitor prompts, outputs and tool calls in production so risky behaviour can be flagged or blocked while a session is active.
Bottom line: LLM security now spans governance, red teaming and runtime controls because attackers are using models inside real criminal workflows.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
24/07/2026 4:15 pm
LLM governance has shifted from model quality to operational control. Once an LLM is used inside fraud, extortion or malware workflows, the core risk is no longer only unsafe content generation. The real issue is who can invoke the model, what data it can reach, and whether its outputs can trigger harmful actions. Practitioners should treat model inventory and access governance as first-order security controls.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
- Organisations that rely heavily on static credentials reported a 20-percentage-point increase in security incidents compared with those with low reliance, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: How do identity and privilege controls apply to agentic AI workflows?
A: They should define what the agent may access, what it may change, and which actions require stronger telemetry or approval. The useful question is not whether the user was authenticated, but whether the delegated authority given to the agent was proportional to the task and visible at the point of execution.
👉 Read our full editorial: LLM security is now a governance problem, not just a model problem