Notifications
Clear all
Topic starter
22/07/2026 4:38 pm
TL;DR: Coding agents now execute commands, modify files, connect to services, and operate through MCP servers, which means traditional AI and endpoint controls often miss the real risk, according to Zenity. The governance challenge is no longer only prompt safety; it is managing high autonomy, high privilege, and approval fatigue in systems that can act before humans can meaningfully review.
NHIMG editorial — based on content published by Zenity: Coding Agents Are Moving Faster Than Security. Here's What CISOs Need to Know
Questions worth separating out
Q: What breaks when coding agents are governed like ordinary AI assistants?
A: The main failure is that ordinary assistant controls assume the system only suggests content, while coding agents can execute actions.
Q: Why do AI agents complicate existing IAM and PAM controls?
A: AI agents complicate IAM and PAM because they often inherit delegated credentials, operate across multiple systems, and keep acting after the initial approval moment has passed.
Q: How do security teams know whether an agent is operating inside its intended boundary?
A: They need evidence for both intent and execution.
Practitioner guidance
- Inventory coding agents as governed identities Classify every coding agent, plugin, MCP server, and connected workflow as a privileged non-human actor with an owner, an allowed action set, and a revocation path.
- Separate setup risk from runtime and execution controls Apply different controls to repository content, live context, and action execution so one compromise does not cascade across all three layers.
- Constrain MCP servers and tool integrations Approve only the minimum tool connections required for a specific agent workflow, then review those integrations as privileged access paths.
What's in the full article
Zenity's full webinar covers the operational detail this post intentionally leaves for the source:
- Live attack demonstration showing how a coding agent can override a defensive control and continue executing a task.
- Extended Q&A on YOLO Mode, MCP security, monitoring, and governance decisions that were only summarised here.
- Researcher walkthrough of the full coding agent threat model across setup, runtime, and execution.
- Practical discussion of how teams can balance developer speed with destructive-action prevention.
👉 Watch Zenity's on-demand webinar on securing coding agents that take action →
Coding agents and MCP access: what security teams are missing?
Explore further
22/07/2026 4:43 pm
Coding agents are becoming non-human identities with action authority, not just assistants. Once a system can execute commands, alter files, and connect to external services, the governance question shifts from content safety to delegated operational authority. That means IAM, PAM, and NHI controls need to reason about task scope, execution scope, and revocation scope together. Practitioners should treat these systems as governed actors, not merely interfaces.
A question worth separating out:
Q: Who is accountable when a coding agent makes an unsafe change?
A: Accountability should sit with the delegating owner of the workflow, the policy administrator who allowed the action, and the platform team that exposed the tool path. If the organisation cannot trace who authorised the task, which tools were available, and why the action was permitted, governance has failed.
👉 Read our full editorial: Coding agents need a different security model for enterprise control
