Export
Confused Deputy Problem
/wiki/confused-deputy-problem
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
With its linksA pack for Claude, ChatGPT, Gemini or NotebookLM, or STIX and CSV, from the console
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
growing ·
7 feeds
Confused Deputy Problem
Agent with legitimate authority executes instructions from mutable, unverified sources, conflating source trust with content authorization
Intelligence coverage
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.
Detection 2
- 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
Mitigated by 1
Frequently mentioned together 14
Sources 13
- Why AI Agent Security Starts With Permissions, Not Prompts · HackerNoon
- The Rise of the Unsanctioned Agent Swarm · DZone
- AI Security Issues Are Social Engineering Issues · Lobsters
- Reported Kubernetes Vulnerabilities Could Expose Google Cloud Tokens and Passwords · LinuxSecurity: Articles
- Do Not Give Every Sub Agent the Parent's Tool Belt · HackerNoon
5 of 13 sources shown · Pro unlocks the full list