Loading...
Loading...
Found 41 Skills
Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI assistant.
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.
Use this skill when auditing AI agent skills for security vulnerabilities, prompt injection, permission abuse, supply chain risks, or structural quality. Triggers on skill review, security audit, skill safety check, prompt injection detection, skill trust verification, skill quality gate, and any task requiring security analysis of AI agent skill files.
Debug and harden production LLM prompts — handle prompt injection, output format drift, instruction forgetting in long contexts, and cross-model portability issues. Use this skill when the user ships an LLM-powered feature to production and needs to diagnose why outputs are inconsistent, unsafe, or regressed after model updates — NOT for basic 'write a better prompt' questions.
Security audit and vulnerability scanning for AI agent skills before installation. Detects prompt injection in SKILL.md files, dangerous code patterns (eval, exec, subprocess), network exfiltration, credential harvesting, dependency supply chain risks, file system boundary violations, and obfuscation. Produces PASS/WARN/FAIL verdicts with remediation guidance. Use when evaluating untrusted skills, pre-install security gates, or auditing skill repositories.
Expert skill for integrating cloud AI APIs (Claude, GPT-4, Gemini). Covers secure API key management, prompt injection prevention, rate limiting, cost optimization, and protection against data exfiltration attacks.
Implements content safety filters with PII redaction, policy constraints, prompt injection detection, and safe refusal templates. Use when adding "content moderation", "safety filters", "PII protection", or "guardrails".
Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill safety, or run a security audit.
Clean AI refusal responses from Codex CLI, Claude Code, and OpenCode session files, and inject CTF/pentest prompts to reduce refusals.
Security auditor for Claude Code skills and agent definitions. Scans a skill or agent directory for prompt injection, data exfiltration, privilege escalation, memory poisoning, obfuscation, malicious persistence, and 12 other threat categories (18 total). Returns a graded verdict (OK / WARNING / CRITICAL) with detailed findings. Use this skill whenever you need to audit, review, or validate the safety of a skill, an agent definition, a system prompt, or any set of instruction files before installing or trusting them. Also use it when the user mentions security scanning, threat detection, prompt injection checking, or wants to verify that a skill is safe. Triggers on: /maton, "audit this skill", "is this skill safe", "check for injection", "scan for threats", "review this agent", "security check".
Protects LLM agent systems in real-time with a 5-tier filter (hash cache, rule engine, ML classifier, LLM judge, human approval) and an async learning engine. Synthesizes new rules from every detected attack, adding less than 50ms latency. Trigger on 'add security layer', 'prevent prompt injection', 'adaptive guard', 'runtime protection', or 'agent security'.