Prompts as Code & Embedded Keys | The Hunt for LLM-Enabled Malware
https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/:

1. As Large Language Models (LLMs) are increasingly incorporated into software‑development workflows, they also have the potential to become powerful new tools for adversaries; as defenders, it is important that we understand the implications of their use and how that use affects the dynamics of the security space.
2. The majority of developers leverage commercial services like OpenAI, Anthropic, Mistral, Deepseek, xAI, or Gemini, and platforms such as HuggingFace, Groq, Fireworks, and Perplexity, rather than hosting and running these models themselves.
3. Crimeware families achieve an unparalleled level of technical sophistication, APT groups are competing in fully-fledged cyber warfare, while once decentralized and scattered threat actors are forming adamant alliances of ...

@secharvester