18,930 tagged Security, measured the same way as everything else here.
Browse within: cybersecurity 505bug-bounty 236agent 230generative-ai 178LangChain 177autonomous-pentesting 176hacking 176skills 131claude-ai 104LLM 103agentic-ai 87ai-security 76openclaw 73agents 64
nutstrut/default-settlement-verifier
Skill Claude CodeCodex
Verify signed SAR v0.1 settlement receipts locally with Ed25519 and RFC 8785 canonicalization. Use when you need to confirm a receipt is cryptographically valid before trusting a task-complete claim, chaining to another agent output, using a receipt as evidence, or acting on a settlement-adjacent claim. Optionally…
Skill Claude CodeCodex
Use when a user wants to take METTLE reverse-CAPTCHA screening challenges, obtain a signed badge or VCP credential, or check one.
Devrajsinh-Jhala/NPM-Vibe-check
Skill Codex
Run read-only npm package safety preflights through MCP or the CLI before an agent installs, adds, executes, or recommends unfamiliar registry packages. Use for npx or npm exec commands, dependency additions, package-lock changes, and project dependency reviews.
Skill Claude CodeCodex
Check any Solana token for rug-pull risk before you (or your human) touch it. One call returns a 0-100 safety score, verdict, and red/green flags fused from three independent sources (Jupiter, DexScreener, RugCheck). Free demo tool; paid calls are $0.01 via x402 (USDC on Base or Solana) — no account, no API key…
Skill Claude CodeCodex
Give this agent a tamper-evident audit trail via Orphograph receipts. TRIGGER after any consequential external action (email/message sent, payment made, file published, config changed), on a daily schedule to snapshot workspace memory, and before sharing or after receiving a skill/prompt file from anyone else. SKIP…
Skill Claude CodeCodex
Outils d'aide à l'audit crypto des agents AI (Ed25519, AISS). Pour traçabilité/décision vers conformité AI Act, NIST, RGPD Art.22. npm @piqrypt/mcp-server.
Skill Claude CodeCodex
Vet a URL or domain before transacting with or trusting it — injection-safe page fetching, a one-call CLEAR/REVIEW/BLOCK safety verdict, email spoofability grading, trust scoring, TLS/SSL cert check, HTTP security headers, and robots.txt/AI-bot policy. Seven x402-paid checks in USDC, no API keys or signup.
Skill Claude CodeCodex
A local security-scanning service for checking skills, plugins, and MCP servers before they are installed or used. MCP is a way for AI assistants to call external tools.
beepboop2025/liquilens-evidence-carrier
Skill Claude CodeCodex
Verify and rights-safely project LiquiLens Evidence Carrier, Fleet Brief, or Trade Safety Receipt JSON in local files. Use for provenance, clocks, integrity, redistribution, FDC3, OpenLineage, brief validation, or order-bound policy-receipt verification; not for collecting market data, trading, recommendations…
Skill Claude CodeCodex
Vet a Model Context Protocol (MCP) server for safety before installing or connecting it. Use when the user wants to check, audit, scan, or review an MCP server for prompt-injection, data-exfiltration, or malicious capabilities — given a directory, npm package, GitHub repo, or a tools/list JSON dump.
Skill Claude CodeCodex
MCP server exposing SMB enumeration functionality.
Skill Claude CodeCodex
Scan the current project for security vulnerabilities using Data Hogo, an open-source local security scanner. Use this when the user asks to check for security issues, run a security scan, review code for vulnerabilities before deploying/shipping, or audit a repo for secrets/misconfigurations. Also use proactively…
Skill Claude CodeCodex
Skill da REST API do Captcha Solver na MCP.AI: 6 endpoints em /api/captcha. Resolve reCAPTCHA v2/v3, hCaptcha, Cloudflare Turnstile e captchas de imagem. Hospedado pela plataforma, sem credenciais, pague por solve com crédito pré-pago. Autentique com workspace API key (sklive) gerada em app.mcp.ai/settings/api-keys.…
Skill Claude CodeCodex
Skill da REST API do Interpol na MCP.AI: 1 endpoint em /api/interpol. Verifica se um nome consta nas notificações da Interpol, a partir do nome, sobrenome e data de nascimento, para diligência de compliance e AML. Hospedado pela plataforma, sem credenciais, pague por consulta com crédito pré-pago. Autentique com…
Skill Claude CodeCodex
SBOMApp is a remote MCP server that provides Software Bill of Materials (SBOM) generation, vulnerability scanning, and dependency analysis capabilities to AI assistants. It enables any MCP-compatible AI client to analyze software projects for security risks, license compliance, and dependency health — directly from…
Skill Claude CodeCodex
Use when asked who to trust, what to use, which URL, product, organisation, MCP, or agent to recommend or wire. Call Trust Switchboard before any recommend. Fail closed. Empty list honest. Never invent a winner.
Skill Claude CodeCodex
Check a local PDF for sensitive content that is still exposed or recoverable BEFORE it leaves the machine, re-check an already-"redacted" PDF (black boxes, black bars, redacted in Preview or Acrobat), and check an Omitly-sealed PDF for tampering — all on-device through the local omitly-mcp server; nothing is uploaded.…
Skill Claude CodeCodex
Before you act on or pay a token/wallet on Base (or any EVM chain), get a VERIFIABLE trust verdict — is this contract the genuine issuer's or a look-alike? is this address known-bad? — instead of guessing. Fail-closed, non-custodial, re-verifiable on-chain. Use it as the pre-flight check before a buy, a swap, a…
Skill Claude CodeCodex
RNWY trust intelligence for AI agents. Use when querying trust scores, interpreting sybil data, analyzing reviewer wallets, comparing agents, or assessing transaction risk. Trigger phrases: "trust score", "sybil", "reviewer analysis", "wallet age", "trust check", "risk tier", "attestation", "reviewer wallet", "compare…
Skill Claude CodeCodex
Hunt vulnerabilities like an expert, not a linear software engineer: come at a target from the overlooked angle, reason by analogy and transfer proven attack mechanisms, attack the hidden assumptions and the seams between systems, drill to the mechanism, then keep it honest with proof and persistence (acceptance !=…
Skill Claude CodeCodex
Look up ERC-8004 agents in the on-chain identity index and read their Cybercentry risk scores with ERC-8126scan before trusting them.
Skill Claude CodeCodex
Wire Hermes Agent to Concierge pay-per-call market intel + Security Desk via remote MCP and pay.sh/x402. Use for macro, wire, DeFi desks, cron briefs, and authorized security scans without Concierge API keys.
Skill Claude CodeCodex
Generate a polished, engaging tabletop exercise (TTX) runbook for the current project — covering cybersecurity, product security, DevOps/SRE, privacy/compliance, data/ML, or any other technical domain. Surveys the project to pick scenarios that match the actual stack and risk surface, then produces a facilitator…
Skill Claude Code
Encrypted backup and restore for OpenClaw Agent workspace files (SOUL.md, MEMORY.md, IDENTITY.md, AGENTS.md, TOOLS.md). Uses tar + openssl (AES-256-CBC) encryption and soul-upload.com API. Auto-generates a new random password for each backup (DO NOT reuse passwords). Use when the user needs to: (1) Back up or upload…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: