Notifications
Clear all
Topic starter
28/08/2026 12:04 pm
TL;DR: The software supply chain is shifting to agentic development, where coding agents write, test, and ship code at machine speed while expanding the attack surface across prompts, plugins, and MCP servers, according to Apiiro. The real control problem is no longer post-hoc detection, but independent prevention and governance across agent-generated code.
NHIMG editorial — based on content published by Apiiro: the shift toward securing agentic development and coding agents as the new perimeter
By the numbers:
- Apiiro says coding agents are driving 5x more code and 10x more risk than scanner-and-triage workflows were designed to handle.
- Apiiro reports that offensive AI agents are discovering exploitable flaws up to 20x faster, compressing the time defenders have to react.
Questions worth separating out
Q: What breaks when coding agents are allowed to generate code without independent governance?
A: Security review arrives too late when code is created faster than humans can inspect it.
Q: Why do AI coding agents increase supply-chain risk?
A: AI coding agents can choose tooling, install packages, and edit lock files in ways that may bypass the controls humans expect in a managed environment.
Q: How do you know if agentic development controls are actually working?
A: Look for evidence that every agent-generated change is checked against the same quality profile, that sandbox findings are traceable, and that remediation loops reduce defects instead of hiding them.
Practitioner guidance
- Enforce pre-commit policy gates for agent-generated code Move security controls into IDE and CLI workflows so prompts are checked against architectural and policy context before code is written or committed.
- Separate code authorship from governance Require an independent control plane that cannot be bypassed by the same coding agent producing the output.
- Inventory agent integrations and privileged inputs List every coding agent, extension, skill, plugin, and MCP server that can influence code creation.
What's in the full article
Apiiro's full analysis covers the operational detail this post intentionally leaves for the source:
- How the AppSec Data Fabric maps code-to-runtime relationships and ties them to business risk.
- How Secure Prompt enriches developer prompts with architectural and policy context before code is generated.
- How Guardian Agent auto-triages and auto-fixes issues before source control ingestion.
- How the control plane is intended to work across multiple coding agents, extensions, and CLI workflows.
👉 Read Apiiro's analysis of software supply chain security for agentic development →
Coding agents and supply chain security: are your controls keeping up?
Explore further
28/08/2026 12:04 pm
Agentic development security now depends on governing software creation before code exists. Once coding agents can design, write, and ship code, the old assumption that AppSec can clean up problems after commit no longer holds. Prevention has to move into the authoring layer, where prompts, policy context, and architectural constraints shape the output before source control ever sees it. That is the real category shift, and practitioners should treat it as a control-plane problem, not a scan problem.
A question worth separating out:
Q: Should organisations treat AI coding agents like privileged software identities?
A: Yes. If an AI agent can install code, access secrets, or modify repositories, it is functionally acting as a privileged non-human identity and should be governed that way. That means task-scoped access, explicit boundaries, and monitoring of its downstream actions, especially when it can touch build and release systems.
👉 Read our full editorial: Agentic coding agents are becoming the new software supply chain perimeter
