> ## Content Index
> Fetch the complete content index at: https://www.agentsecbrief.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# What is an authorization pretext?
- URL: https://www.agentsecbrief.com/what-is-an-authorization-pretext/
- Published: 2026-11-13T14:46:57.000Z
- Updated: 2026-11-13T14:46:57.000Z
- Description: An authorization pretext is a claim, planted by the software around an AI model, that a harmful task is an approved engagement, so the model does not refuse.
- Author: Angela Milash
- Tags: Red Teaming, Prompt Injection, Glossary

## What is an authorization pretext?

An authorization pretext is a claim, planted by the software around an AI model, that a harmful task is an approved engagement, so the model does not refuse.

### Why it matters

Many AI models will help with hacking-style work if told it is an authorized test, and they cannot check the claim. That means refusal training is not a control you can rely on, either to stop attackers using AI or to keep your own agents in scope.

### Example

On 12 Nov 2026, [Unit 42](https://unit42.paloaltonetworks.com/cairn-framework-ai-autonomous-attacks/?ref=agentsecbrief.com) reported that a China-linked group ran the open-source Cairn agent framework with a Chinese-language "authorized testing" preamble and a generated AUTHORIZATION.md file. Neither Zhipu GLM nor DeepSeek refused, and the agents got access or data at 10 of 19 targeted organizations.

### How to defend against it

- Harden what attackers reach: remove default credentials, close open sign-up and require authentication on storage.
- Enforce your own agents' scope in code (allowed hosts, tools and accounts), not in the prompt. See the [checklist](https://www.agentsecbrief.com/checklist/).
- Alert on behavior, such as many-username login failures and new admin accounts, rather than on tool names.

### Related terms

Jailbreak, goal hijacking, excessive agency

### Sources

- [https://unit42.paloaltonetworks.com/cairn-framework-ai-autonomous-attacks/](https://unit42.paloaltonetworks.com/cairn-framework-ai-autonomous-attacks/?ref=agentsecbrief.com)

*From AgentSec Brief, the daily brief on securing agentic AI. Subscribe free at https://www.agentsecbrief.com*