Download

Skill UI

Browse and discover 6932+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Prompt Injection , found 10 results

Default Newest Most Downloaded

LangChain Security Practices

langchain-security-basics

jeremylongshore/claude-code-plugins-plus-skills

Guides securing LangChain deployments with secrets management, prompt injection mitigation, safe tool execution, output validation, and audit logging for production readiness.

Prompt Guard Detector

Orchestra-Research/AI-Research-SKILLs

Meta’s Prompt Guard is an 86M-parameter classifier that spots prompt injections and jailbreak attempts before they reach LLMs, filtering user input, third-party data, or RAG documents with multilingual support and sub-2ms latency for fast deployments.

Agentic Actions Auditor

agentic-actions-auditor

trailofbits/skills

Audits GitHub Actions workflows that invoke AI coding agents to surface prompt injection and sandbox risks, tracing attacker-controlled inputs through env vars, reusable actions, and workflow references before deployment or code review.

Skill Security Scanner

sickn33/antigravity-awesome-skills

Scans a Claude skill directory for security risks before adoption, detecting prompt injection, malicious code, overbroad permissions, secrets, and supply-chain issues via the bundled scan_skill.py tool, and supports a manual review workflow.

Mortgage Security Guardrails

security-guardrails

davepoon/buildwithclaude

Security guardrails embedded in the mortgage plugin that block prompt injection and social-engineering tricks, stop system prompt extraction, guard PII and pricing logic, enforce workflow phases, and ensure conversational inputs stay within refinance scope.

Prompt Injection Defense Detector

detecting-ai-model-prompt-injection-attacks

mukul975/Anthropic-Cybersecurity-Skills

Combines regex signatures, heuristic scoring, and a DeBERTa classifier to detect prompt injection attempts against LLM-based applications, flagging or blocking malicious inputs before they reach the model and fitting into validation layers, audits, or incident response workflows.

LLM Security Guardrails

implementing-llm-guardrails-for-security

mukul975/Anthropic-Cybersecurity-Skills

Builds NeMo Guardrails-based input/output validation pipelines to block prompt injection, redact PII, enforce content policies, and verify structured outputs so LLM-powered services stay safe before downstream use.

AI Security Assessment

alirezarezvani/claude-skills

Assesses AI/ML systems for prompt injection, jailbreak, model inversion, data poisoning, and agent tool abuse using MITRE ATLAS mapping, signature detection, and scoring metrics before deployment.

Agent ASI Compliance Check

agent-owasp-compliance

github/awesome-copilot

Checks AI agent implementations against the OWASP Agentic Security Initiative Top 10 risks, producing findings on controls, vulnerabilities, and recommendations for prompt injection, tool governance, escalation, logging, identity, policy, supply chain, and behavioral monitoring before production or audit.

Prompt Safety Review

ai-prompt-engineering-safety-review

github/awesome-copilot

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

1

Language