Prompt Injection skills
Free agent skills tagged prompt injection, ready to install into any SKILL.md-compatible agent.
7 skills
Defending LLMs with Guardrails
mukul975
Enhance LLM safety with runtime guardrails.
Security & ComplianceintermediatePython · Shell27.6k repo
Orchestrating LLM Attacks with PyRIT
mukul975
Automate multi-turn adversarial attacks against LLMs.
Security & ComplianceadvancedPython · Shell27.6k repo
G
G0DM0D3 Jailbreaking
nousresearch
Bypass safety filters on API-served LLMs with ease.
AI & AgentsintermediatePython · Shell228.5k repo
Detecting AI Model Prompt Injection Attacks
mukul975
Enhance LLM security with prompt injection detection.
Security & ComplianceintermediatePython · Shell27.6k repo
AI Security
alirezarezvani
Assess AI/ML systems for vulnerabilities and risks.
Security & ComplianceintermediatePython · Shell24.3k repo
LLM Security Testing
zhaoxuya520
Assess security for LLM applications and AI agents.
Security & ComplianceadvancedPython · Node23.4k repo
Skill Security Scanner
getsentry
Ensure agent skills are safe before installation.
Security & ComplianceintermediatePython · Node · Shell907 repo