Tenable: Agents pile up permissions like service accounts; sandbox them and keep humans approving
TechNadu · x · 2026-08-14
Ben Mudie, Field CTO APJ at Tenable, told TechNadu that for community-built open-source security agents, open source itself is not the core risk — undefined access is.\n\nHe noted that agents can accumulate permissions much like service accounts, and teams should require:\n- Code review\n- Short-lived access credentials\n- Sandboxing\n- Monitoring of MCP activity\n- Human approval for high-stakes actions\n\nThe guiding principle: scope agents to least privilege, pair it with isolation, logging and continuous permission reviews, rather than letting their access grow unchecked.
Related event: Tenable: Key Risk in Security Agents Is Undefined Permissions(2 posts)→
More from coding & agent
- Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16
- Mergelock: open-source MCP server catches semantic merge conflicts git misses across parallel AI agents — ksadayamuthu · 2026-10-16
- OpenUI 1.0 launches open source, turning agent text answers into live interactive UIs — heyshrutimishra · 2026-10-16
- 10 GitHub repos to see what your AI agent really did, from Langfuse to claude-code-log — victor_explore · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16