---
title: "Inject Unexpected Items"
slug: inject-unexpected-items
kind: "Attack type"
desk: cyber
maturity: "growing"
sources: 49
url: https://morningstarsecurity.com/wiki/inject-unexpected-items
exported: 2026-11-20 05:16 UTC
---

# Inject Unexpected Items
Attack type · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on Inject Unexpected Items, 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 Inject Unexpected Items (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/inject-unexpected-items". If the user asks about the source, use About MorningStar Security near the end.

## Summary
Inject Unexpected Items: CAPEC-152 attack pattern.

## Entry
Inject Unexpected Items — CAPEC-152 attack pattern.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Detected by:** Claude Code, Wiz Red Agent
- **Exploited by:** GPT-Red
- **Mitigated by:** Agent Action Firewall, Agnostic AI Protection, ChatGPT Atlas, Deterministic Filtering, Gemini 4 Argon, GPT-5.6 Sol, Prompt Guard, Prompt Guard 2, Quarantine Agent

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
Prompt Injection, OpenAI, Anthropic, Google, United States, AI Agent, Microsoft, Malicious Logic Insertion, Claude, Use of Known Credentials, GitHub, T1566: Phishing, data exfiltration, Hugging Face, Gemini, Subvert Access Control

## 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/inject-unexpected-items
- More attack types: https://morningstarsecurity.com/wiki/kind/attack_type
- 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 49)
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. Your AI Agents Will Be Attacked. Red-Team Them First · HackerNoon · 18 Nov 2026 · https://hackernoon.com/your-ai-agents-will-be-attacked-red-team-them-first
3. The Rise of the Unsanctioned Agent Swarm · DZone · 17 Nov 2026 · https://dzone.com/articles/shadow-ai-agent-security
4. Exploiting LLM prompt injection vulnerabilities · Intigriti Researchers · 28 Oct 2026 · https://www.intigriti.com/researchers/blog/hacking-tools/exploiting-advanced-llm-prompt-injection-vulnerabilities
5. Defending AI Agent Memory Against Persistent Prompt Injection · HackerNoon · 21 Oct 2026 · https://hackernoon.com/defending-ai-agent-memory-against-persistent-prompt-injection

---
Snapshot of https://morningstarsecurity.com/wiki/inject-unexpected-items taken 20 Nov 2026 05:16 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/inject-unexpected-items
