ai-driven-dev-wiki
Search
Search
Dark mode
Light mode
Explorer
prompt-injection
42 items with this tag.
Oct 16, 2026
Function calling using LLMs
tool-use
agents
prompt-injection
mcp
Oct 16, 2026
Open-Prompt-Injection
prompt-injection
security
benchmark
llm
Oct 16, 2026
Model Armor
agent-safety
guardrails
prompt-injection
security
Oct 16, 2026
LlamaFirewall
security
prompt-injection
guardrails
agents
Oct 16, 2026
StruQ: Defending Against Prompt Injection with Structured Queries
llm
security
prompt-injection
agent-safety
evaluation
Oct 16, 2026
MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
mcp
security
agents
prompt-injection
Oct 16, 2026
LlamaFirewall: An open source guardrail system for building secure AI agents
security
prompt-injection
guardrails
agents
Oct 16, 2026
Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
prompt-injection
agent-safety
web-agents
Oct 16, 2026
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
security
agents
prompt-injection
survey
Oct 16, 2026
Structured Query
llm
security
prompt-injection
agent-safety
Oct 16, 2026
Structured Instruction Tuning
llm
security
prompt-injection
agent-safety
Oct 16, 2026
Source-Sink Analysis
security
prompt-injection
agent-safety
Oct 16, 2026
Safe Url
security
prompt-injection
agent-safety
exfiltration
Oct 16, 2026
Role Confusion
prompt-injection
jailbreaking
llm-security
Oct 16, 2026
Prompt Leaking
security
prompt-injection
llm
Oct 16, 2026
Plan-Then-Execute Pattern
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
Permission Modes
agent-safety
human-oversight
agent-tooling
prompt-injection
Oct 16, 2026
LLM Map-Reduce Pattern
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
Lethal Trifecta
agent-security
prompt-injection
tool-use
exfiltration
Oct 16, 2026
Indirect Prompt Injection
agents
agent-safety
security
prompt-injection
Oct 16, 2026
Indirect AGENTS.md Injection
agents
agent-safety
security
prompt-injection
supply-chain
Oct 16, 2026
Implicit Tool Poisoning
mcp
security
agents
prompt-injection
Oct 16, 2026
Direct Prompt Injection
security
prompt-injection
llm
agent-safety
Oct 16, 2026
Control-Data Plane Confusion
llm
security
prompt-injection
Oct 16, 2026
Context-Minimization Pattern
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
Completion Attack
llm
security
prompt-injection
agent-safety
response
Oct 16, 2026
Code-Then-Execute Pattern
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
Action-Selector Pattern
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
The lethal trifecta for AI agents: private data, untrusted content, and external communication
agent-security
prompt-injection
exfiltration
tool-use
Oct 16, 2026
Securing LLM Systems Against Prompt Injection
llm
security
prompt-injection
tool-use
Oct 16, 2026
Prompt injection attacks against GPT-3
security
prompt-injection
llm
Oct 16, 2026
Prompt Injection as Role Confusion
prompt-injection
jailbreaking
llm-security
Oct 16, 2026
Mitigating the risk of prompt injections in browser use
prompt-injection
agent-safety
security
Oct 16, 2026
Mitigating Prompt Injection Attacks in Software Agents
coding-agents
agent-safety
security
prompt-injection
sandboxing
Oct 16, 2026
Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments
agents
agent-safety
security
prompt-injection
supply-chain
Oct 16, 2026
How GitHub's agentic security principles make our AI agents as secure as possible
agent-safety
security
prompt-injection
guardrails
human-oversight
Oct 16, 2026
Exercise caution when building off LLMs
llm
security
prompt-injection
governance
Oct 16, 2026
Prüfen Coding-Agents Lizenzen?
open-source-licensing
prompt-injection
harness-engineering
supply-chain
Oct 16, 2026
Designing AI agents to resist prompt injection
security
prompt-injection
agent-safety
Oct 16, 2026
Design Patterns for Securing LLM Agents against Prompt Injections
security
prompt-injection
agent-architecture
agent-safety
Oct 16, 2026
Build zero-trust AI agents that judge intent, not just syntax
agent-safety
guardrails
governance
prompt-injection
security
Oct 16, 2026
Agent pull requests are everywhere. Here's how to review them.
agents
code-review
agent-safety
prompt-injection
human-oversight