# Five Eyes Issue Joint Security Guidance on Agentic AI Deployment Risks

> The Five Eyes intelligence partners have issued their first coordinated security guidance on agentic AI, the systems that do not just answer questions but take actions on a user's behalf. Cybersecurity agencies from the US, UK, Australia, Canada, and New Zealand, including CISA and the NSA, jointly published the document on May 1, and the tone is cautious rather than celebratory. The guidance sorts the danger into five categories, covering privilege, design and configuration, behavior, structure, and accountability, and catalogs more than twenty three distinct risks alongside over a hundred recommended practices. The standout warning concerns prompt injection, which the agencies call the most persistent and difficult to fix threat, noting that defenses remain immature and that no single control is enough on its own. Their core recommendation is restraint: adopt agents slowly, start only with low risk tasks, and wrap everything in strong governance, monitoring, and human oversight. Coming from the governments that set procurement and security norms for much of the Western world, this reads as an early brake on the rush to hand real authority to autonomous software.

_Section: [Daily AI Updates](https://www.wortins.com/daily-ai) · Source: Hunton Andrews Kurth · Published Saturday, July 11, 2026_

## Wortins' read

The Five Eyes intelligence partners have issued their first coordinated security guidance on agentic AI, the systems that do not just answer questions but take actions on a user's behalf. Cybersecurity agencies from the US, UK, Australia, Canada, and New Zealand, including CISA and the NSA, jointly published the document on May 1, and the tone is cautious rather than celebratory. The guidance sorts the danger into five categories, covering privilege, design and configuration, behavior, structure, and accountability, and catalogs more than twenty three distinct risks alongside over a hundred recommended practices. The standout warning concerns prompt injection, which the agencies call the most persistent and difficult to fix threat, noting that defenses remain immature and that no single control is enough on its own. Their core recommendation is restraint: adopt agents slowly, start only with low risk tasks, and wrap everything in strong governance, monitoring, and human oversight. Coming from the governments that set procurement and security norms for much of the Western world, this reads as an early brake on the rush to hand real authority to autonomous software.

## Source

[Read the full story at Hunton Andrews Kurth](https://www.hunton.com/privacy-and-cybersecurity-law-blog/cybersecurity-authorities-issue-joint-guidance-on-the-adoption-of-agentic-ai-systems)

## Related coverage

- [AI Now Used in Real Cyberattacks: 73% of Orgs Feel Impact of AI-Powered Threats](https://www.wortins.com/story/ai-now-used-in-real-cyberattacks-73-of-orgs-feel-impact-of-a-fe3f57e4) — [NetEye](https://www.neteye-blog.com/blog/2026/07/03/the-ai-cyber-attacks-explosion-in-2026-emerging-threats/)
- [Google Delays Gemini 3.5 Pro, Rebuilds Architecture for Math and Long Context](https://www.wortins.com/story/google-delays-gemini-3-5-pro-rebuilds-architecture-for-math--cc3e34a0) — [BigGo Finance](https://finance.biggo.com/news/6f0c6bb2-795f-4c57-9d09-6db691d7638a)
- [California Governor Deploys Claude AI Across All State Agencies at 50% Discount](https://www.wortins.com/story/california-governor-deploys-claude-ai-across-all-state-agenc-678f8ae8) — [California Governor](https://www.gov.ca.gov/2026/06/29/governor-newsom-announces-a-first-of-its-kind-partnership-providing-anthropic-tools-to-state-agencies-and-improving-services-for-californians/)
- [Cursor 3 Launches Parallel AI Agents Window for 30-50% Speed Gain on Coding](https://www.wortins.com/story/cursor-3-launches-parallel-ai-agents-window-for-30-50-speed--74984074) — [Cursor Blog](https://cursor.com/blog/cursor-3)
- [Claude Sonnet 5 Becomes Default Model, Agentic Capabilities Near Opus Level](https://www.wortins.com/story/claude-sonnet-5-becomes-default-model-agentic-capabilities-n-c66572f0) — [Anthropic](https://www.anthropic.com/news/claude-sonnet-5)
- [2026 Defined as Year of AI Agents: 40% of Enterprise Apps Expected to Have Agents by Year-End](https://www.wortins.com/story/2026-defined-as-year-of-ai-agents-40-of-enterprise-apps-expe-3abafd08) — [Hector Pincheira](https://www.hectorpincheira.com/en/news/technological-radar-july-2026-ai-agents-go-into-production-and-governance-doesnt-keep-up)

---

_Curated and written by [Wortins](https://www.wortins.com) — The daily AI briefing. Every story links to its original source; the "Wortins read" on each is our own original analysis. [About Wortins & our editorial approach](https://www.wortins.com/about)._