llm-security
llm-security is an data AI skill with a core value of Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM. It
helps developers solve real-world problems in the data domain, boosting
efficiency, automating repetitive tasks, and optimizing workflows.
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM
Quick Facts
mkdir -p ./skills/llm-security && curl -sfL https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/skills/llm-security/SKILL.md -o ./skills/llm-security/SKILL.mdRun in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM
🎯 Best For
- Security auditors
- DevSecOps teams
- Compliance officers
- Claude users
- Data professionals
💡 Use Cases
- Auditing dependencies for known CVEs
- Scanning API endpoints for auth gaps
- Data pipeline auditing
- Query optimization
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply llm-security to Your Work
Provide context for your task — paste source material, describe your audience, or share existing work to guide the AI.
- 4
Review and Refine
Edit the AI output for accuracy, tone, and completeness. Add human insight where the AI lacks context.
❓ Frequently Asked Questions
Can this replace a dedicated SAST tool?
AI-based security review is complementary to SAST tools. Use it as a first-pass filter, not a replacement.
How do I install llm-security?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/llm-security/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Only scanning surface-level issues
Deep security review requires understanding your app architecture, not just regex patterns.
Ignoring data quality
AI analysis inherits all data quality issues — profile your data first.