Dev, web & IT
Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.
Treat retrieved emails, pages, files and tool results as untrusted data. Enforce minimal permissions and approved destinations in the application, require review for consequential actions, and test those boundaries. Model screening and prompts are additional defenses, not complete protection.
Agents that read untrusted content and also have tools are exposed to prompt injection. OWASP lists it as LLM01 in its 2025 Top 10 for LLM applications.
Sample permissions matrix (IonBin’s illustration, not a standard):
| Agent reads | May access | Needs approval |
|---|---|---|
| Public web pages | Read-only search | Any outbound message |
| Your inbox | Drafts only | Sending, forwarding |
| Shared documents | Read and comment | Editing, sharing externally |
| CRM records | Read, draft updates | Writing changes, deletes |
Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.
Hand repeat admin (receipts, logs, notices, handoffs) to workflows your agent can trigger.
Not tool-specific. See Agent-ready for connector support by tool.
Levels come from each tool's recorded, sourced compatibility. How the levels work.
Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.
IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “How do I protect an AI agent from prompt injection?”? Email us with a link to a primary source.
Suggest an edit by email or write to contact@ionbin.com