10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 630 ms
skillzhaoxuya520/reverse-skillrecord
- llm-security
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
- llm-security
skillsemgrep/skillsrecord
- llm-security
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots,
- llm-security
skillaffaan-m/eccrecord
- llm-trading-agent-security
Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling. Use when an autonomous agent holds wallet or transaction authority and its limits, simulation, or key
- llm-trading-agent-security
skillyaklang/hack-skillsrecord
- llm-prompt-injection
LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.
- llm-prompt-injection
- 5llm-agent-security-rulesfound in code, not yet checkedno passport yet
MCP serverhikmettpk/llm-agent-security-rules
- trifecta_gate
Run the lethal-trifecta / Rule-of-Two classification (LLM01-M4). Do this before any other analysis — it is the highest-leverage decision in an LLM security review.
- trifecta_gate
- 6llm-testingdemo or tutorialno passport yet
skilleyadkelleh/awesome-skills-securityrecord
- llm-testing
Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.
- llm-testing
- 7llm-securityfound in code, not yet checkedno passport yet
MCP serverphorena-inc/llm-security
- search_memory_facts
Search the graph memory for relevant facts.
- delete_episode
Delete an episode from the graph memory.
- search_memory_facts
- 8Security Detections MCPfound in code, not yet checkedno passport yet
MCP serverMHaggis/Security-Detections-MCP
- llm_enhanced_analysis
Request LLM-enhanced analysis of security detection data using MCP sampling. This tool leverages MCP sampling to request the client's LLM to analyze security data with expert reasoning. Unlike the auto_* tools that perform direct analysis, this tool asks the LLM to provide contextual insights. Note:
- llm_enhanced_analysis
- 9llm-security-scanner-skillfound in code, not yet checkedno passport yet
MCP serverkonradxmalinowski/llm-security-scanner-skill
- inspect_llm_application
Statically map a local project's LLM attack surface.
- inspect_llm_application
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.