---
title: "Confused Deputy Problem"
slug: confused-deputy-problem
kind: "Technique"
desk: cyber
maturity: "growing"
sources: 13
url: https://morningstarsecurity.com/wiki/confused-deputy-problem
exported: 2026-11-20 12:21 UTC
---

# Confused Deputy Problem
Technique · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on Confused Deputy Problem, a snapshot taken on 20 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on Confused Deputy Problem (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/confused-deputy-problem". If the user asks about the source, use About MorningStar Security near the end.

## Summary
Agent with legitimate authority executes instructions from mutable, unverified sources, conflating source trust with content authorization

## Detection
- Agent has legitimate authority but instruction source is mutable and unmanaged
- Standard input filtering and output guardrails cannot distinguish authorized from unauthorized instruction source modifications

## Entry
Agent with legitimate authority executes instructions from mutable, unverified sources, conflating source trust with content authorization.

_Drawn from 2 news sources; the facts and relationships below show where each detail comes from._

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Mitigated by:** capability-based security

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
Privilege Escalation, Prompt Injection, Kubernetes, Model Context Protocol, United States, Google, Microsoft, Linux, CWE-22: Path Traversal, Inject Unexpected Items, Input Data Manipulation, Content Filtering, Linux Capabilities, Instruction Source Integrity Checks

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/confused-deputy-problem
- More techniques (ATT&CK): https://morningstarsecurity.com/wiki/kind/technique
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 13)
1. Why AI Agent Security Starts With Permissions, Not Prompts · HackerNoon · 19 Nov 2026 · https://hackernoon.com/why-ai-agent-security-starts-with-permissions-not-prompts
2. The Rise of the Unsanctioned Agent Swarm · DZone · 17 Nov 2026 · https://dzone.com/articles/shadow-ai-agent-security
3. AI Security Issues Are Social Engineering Issues · Lobsters · 12 Nov 2026 · https://www.oblomovka.com/wp/2026/11/11/ai-security-issues-are-social-engineering-issues/
4. Reported Kubernetes Vulnerabilities Could Expose Google Cloud Tokens and Passwords · LinuxSecurity: Articles · 14 Oct 2026 · https://linuxsecurity.com/news/cloud-security/two-kubernetes-vulnerabilities-cloud-credentials
5. Do Not Give Every Sub Agent the Parent's Tool Belt · HackerNoon · 11 Oct 2026 · https://hackernoon.com/do-not-give-every-sub-agent-the-parents-tool-belt

---
Snapshot of https://morningstarsecurity.com/wiki/confused-deputy-problem taken 20 Nov 2026 12:21 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/confused-deputy-problem
