AgentFence
StaleDescription
An open-source platform for automatically testing AI agent security. Identifies vulnerabilities such as prompt injection, secret leakage, and system instruction exposure.
Related Projects
Spikee
183 · Python
Simple Prompt Injection Kit for Evaluation and Exploitation. Helps security teams quickly validate defense effectiveness against prompt injection vulnerabilities.
prompt-injectionsecurity-testingexploitation +2
0DIN Sidekick
27 · JavaScript
Firefox/Chromium extension for AI security researchers that streamlines LLM jailbreak testing and vulnerability discovery across multiple providers.
ai-safetyred-teamingjailbreak +2
SCAM
105 · Python
Security Comprehension Awareness Measure by 1Password. An open-source benchmark testing AI agents' security awareness during realistic, multi-turn workplace tasks.
security-benchmarkagent-safetyworkplace +2
AIGoat
53 · JavaScript
Open-source AI security playground for LLM red teaming with hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.
ai-safetyred-teamingowasp +2