Menu

View

JournalDigital

Theme

LightDarkSystem

Text size

AAA

The paper in your inbox every morning

Straight from the source · Glossary

The Tech Gazette

Prompt injection

An attack that hides instructions in text a model reads (a web page, an e-mail, a file) so it does something its user did not ask for.

Read more at en.wikipedia.org →

Learn it

1. AnacondaOct 5, 2026Technical Guides
   The Hidden Line in the Footer: How to Stop AI Agents From Following Bad Instructions

In the news

1. Datadog Security LabsOct 15, 2026Security Desk
   Jev as a judge: How counterfeit policy steers Jev
2. DockerOct 14, 2026News
   AI Agent Security Risks: What Can Go Wrong When Agents Act on Their Own
3. arXiv (systems & security) cs.CROct 13, 2026Research
   Towards Safe Autonomy for Computer Use
4. arXiv (systems & security) cs.CROct 8, 2026Research
   LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
5. IncidentGitHub Advisories (npm)Oct 7, 2026Security Desk
   Critical: Flowise Prompt Injection to RCE and SSRF via CSV/Airtable Agent Python Validator Bypass
6. arXiv cs.SEOct 7, 2026Research
   AgentTracer: Tracing Indirect Prompt Injection Attack through Fine-Grained Intention-Execution Alignment
7. arXiv cs.CLOct 6, 2026Research
   AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
8. Bishop FoxOct 6, 2026Security Desk
   Why the AI Attack Surface Extends Your Stack
9. New RelicOct 6, 2026News
   Introducing AI Observability for OpenTelemetry
10. arXiv (systems & security) cs.CROct 6, 2026Research
    Surviving the Router: Optimizing Skill Injections for Retrieval and Execution
11. arXiv (systems & security) cs.CROct 5, 2026Research
    RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
12. arXiv (systems & security) cs.CROct 2, 2026Research
    Securing Computer-Use Agents Against Branch Steering Attacks
13. arXiv (systems & security) cs.CRSep 30, 2026Research
    Aletheia: Permission-Minimality Testing for Coding-Agent Rules
14. arXiv (systems & security) cs.CRSep 29, 2026Research
    Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
15. arXiv (systems & security) cs.CRSep 29, 2026Research
    ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
16. arXiv (systems & security) cs.LGSep 27, 2026Research
    Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
17. arXiv (systems & security) cs.CRSep 27, 2026Research
    Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation
18. arXiv (systems & security) cs.CRSep 26, 2026Research
    Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection
19. arXiv (systems & security) cs.CRSep 25, 2026Research
    MetaPermit: Scalable and Auditable Access Control for AI Agents via LLM-Inferred Meta-Attributes
20. arXiv (systems & security) cs.AISep 24, 2026Research
    ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation