AI Awesome
Home
Discover the Best AI Tools
Your ultimate directory for finding the right artificial intelligence solutions for any task.
Search
AI Content Detector
(7)
P
unknown
Prompt Injection Sentinel
A model fine-tuned for detecting prompt injection and jailbreaks with a low false-positive rate.
AI Content Detector
fine-tuned BERT-large model
low false-positive rate
prompt injection classification
D
unknown
DeBERTa Prompt Injection Detector v2
DeBERTa Prompt Injection Detector v2 is an AI model fine-tuned for detecting prompt injection attacks in large language models.
AI Content Detector
fine-tuned DeBERTa-v3-base
used in LLM guardrail pipelines
effective at identifying malicious prompts
L
unknown
Llama-Prompt-Guard-2-86M
Llama-Prompt-Guard-2-86M is a lightweight model for detecting prompt injection and jailbreak attempts in LLM pipelines.
AI Content Detector
detects prompt injection
prevents jailbreak attempts
86M parameter model
L
unknown
Llama-Guard-4-12B
Llama-Guard-4-12B is a multimodal safety classifier for detecting harmful content in LLM inputs and outputs.
AI Content Detector
detects harmful content in text and image modalities
developed by Meta
latest in multimodal safety classification
G
open source
GUCCI-atlasv/skillssafe-mcp
A free AI agent skill security scanner that analyzes SKILL.md, MCP configs, and system prompts for security vulnerabilities.
AI Content Detector
Scans for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators
Supports OpenClaw, Claude Code, Cursor, and Codex
No signup required
J
open source
joergmichno/clawguard-mcp
A security scanner for AI agents that detects prompt injections using 42+ regex patterns
AI Content Detector
detects prompt injections
uses 42+ regex patterns
security scanner for AI agents
K
open source
Kaggle-Llm-Detect_Ai_Generated_Text
A tool to detect AI-generated text using machine learning models.
AI Content Detector
detects AI-generated text
uses machine learning models
provides accuracy reports