Skills tagged "prompt-injection"

red-teaming-llms-with-garak - Red-Teaming LLMs with garak
ai-security llm-red-teaming garak prompt-injection
★ 2 · Updated 2026-09-24
Runs NVIDIA garak probe suites against an LLM endpoint and interprets the resulting hit-rate report.
⚙ Enumerate probes and detectors ⚙ Configure target LLM endpoints ⚙ Run security probe suites
prompt-guard - Advanced AI Agent Runtime Security Defense
security prompt-injection runtime-security defense
★ 176 · Updated 2026-09-20
Analyzes inputs and outputs using tiered pattern matching to block prompt injections, supply chain attacks, and memory poisoning.
⚙ Analyze agent input messages ⚙ Scan LLM output content ⚙ Sanitize LLM output content
anth-security-basics - Apply Anthropic Claude API security best practices.
security anthropic claude api-key
★ 17 · Updated 2026-09-19
Applies Anthropic Claude API security best practices for key management, input validation, and prompt injection defense.
⚙ Manage API keys securely ⚙ Rotate API keys safely ⚙ Defend against prompt injections
deepsafe-scan - Preflight security scanner for AI coding agents
security audit scanner openclaw
★ 76 · Updated 2026-09-16
Scans AI agent configs, skills, memory, and model behavior for security risks, secret leaks, PII, prompt injections, and dangerous patterns.
⚙ Scan deployment configuration ⚙ Scan skills and MCP servers ⚙ Scan memory for secrets and PII
llm-security - LLM and AI Agent Security Assessment
llm-security ai-security prompt-injection agent-security
★ 1 · Updated 2026-09-16
Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, and supply-chain risks.
⚙ Reconnoiter AI attack surfaces ⚙ Test prompt injection vulnerabilities ⚙ Test tool abuse risks
agent-guard - Real-time security framework for AI agents
security prompt-injection command-injection openclaw-skill
★ 1 · Updated 2026-09-15
Provides real-time prompt injection detection, command injection blocking, and content sanitization for AI agents.
⚙ Analyze text for security threats ⚙ Sanitize dangerous content from text ⚙ Screen GitHub issues for attacks
PromptInjection - LLM Prompt Injection Security Testing
prompt-injection LLM-security jailbreak-testing security-assessment
★ 12 · Updated 2026-05-11
Test LLM applications for prompt injection vulnerabilities and security risks
⚙ execute direct injection tests ⚙ execute indirect injection tests ⚙ execute multi-stage attacks
sentinel-prompt-protection - Sentinel: SOTA Model for Prompt Injection Protection
security prompt-injection LLM-safety classification
★ 6 · Updated 2026-05-09
Deploy binary classifier using ModernBERT to detect prompt injection attacks
⚙ classify prompts ⚙ detect injections ⚙ predict malicious probability