Running agents in VMs turns the threat internal, security researcher warns
wavefnx · x · 2026-11-13
A security researcher warns that putting AI agents inside VMs changes the threat model: the threat is no longer only external — agents can become internal threats. He adds that many VM offerings are quickly slopped together to sell, urging practitioners to review, understand and run their infra carefully and weigh the pros and cons themselves.
More from coding & agent
- Open-source getmcp-cli turns 1,280-endpoint OpenAPI specs into 25-tool MCP servers, cutting tool tokens from 263k to 6k — Worried-Barracuda845 · 2026-11-13
- Formal verification is the Rust of software correctness — LLMs are making people write specs — arpit_bhayani · 2026-11-13
- whats-in-my-claude: open-source local visualizer for Claude Code's .claude folder, runs fully offline via npx — Srqi · 2026-11-13
- AuralKit 3.0: on-device Swift transcription of video audio tracks with timestamps — rudrank · 2026-11-13
- Delulu Bio adds an MCP server to its free link-in-bio tool, letting Claude manage your page by voice — delulu_intern · 2026-11-13
- Custom motion-director skill turns any voiceover into 1080x1920 motion-graphics animations with Gemini Spark — mijozakinho_2 · 2026-11-13