# AI agent governance: Prompt injection depends on the surface, not the model

DevFeed: [AI agent governance: Prompt injection depends on the surface, not the model](<https://devfeed.tech/articles/ai-agent-governance-prompt-injection-depends-on-the-surface-not-the-model-15995.md>)

Original publisher: [Read original article](<https://workos.com/blog/ai-agent-governance-prompt-injection-surface-not-model>)

Author: WorkOS

Published: 2026-08-06T00:00:00Z

Content type: opinion

Language: en

Sources: [WorkOS Blog](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [browser](<https://devfeed.tech/topics/browser.md>), [GUI](<https://devfeed.tech/topics/gui.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [coding](<https://devfeed.tech/tags/coding.md>), [governance](<https://devfeed.tech/tags/governance.md>), [gui](<https://devfeed.tech/tags/gui.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>)

## AI overview

The article argues that prompt-injection risk for AI agents depends heavily on the actions and access available in their environment, not only on the underlying model. It cites Anthropic results showing attack success varying from 0 percent in a constrained coding environment to 78.6 percent in a broader GUI environment, and notes that even a 1 percent rate remains meaningful for repeatedly attacked browser agents.

## Source excerpt

Anthropic's own data shows one model scoring a 0 percent attack success rate in one environment and 78.6 percent in another. Only the available actions changed.