All projects matching “detect”

AI Security Guard content scanner. Detects prompt injection, intent drift, and credential exfiltration. $0.0015-$0.024 by size. Full docs: https://aisecurityguard.io/v1/skill

Stateful pre-payment firewall for autonomous agents. Enforce caller-supplied amount/network budgets, detect repeated intents, seller pay-to/network drift and large price jumps. Never signs or sends the downstream payment.

Detect the structure of a book manuscript before typesetting it: the chapter list our engine will use (numbered / unnumbered), words and scene breaks per chapter, paragraph count, characters the book font cannot print, and the warnings a full build would raise. Same parser as /v1/typeset, so what you see here is exactly how the book will be divided.

Technical SEO audit of one page: HTTP status, redirect chain, title and meta description length, H1 count, canonical, robots meta, hreflang, Open Graph and Twitter tags, JSON-LD types, images without alt text, link counts, security headers (HSTS, CSP, X-Frame-Options), technology detection (CMS, framework, analytics, CDN) and a prioritised issue list with a 0-100 score. Static HTML only; honours r

Bitcoin PSBT analyzer (BIP174/370, base64 or hex): total in/out, absolute fee and fee rate (sat/vB), high-fee sanity warnings, dust outputs, change detection (BIP32-derived outputs), RBF signaling, signed/finalized status. Read-only; nothing is broadcast or stored.

Pre-trade safety in one keyless call, chain auto-detected. Solana: quotes a real buy-then-sell round trip through Jupiter routing (sell route exists? round-trip loss %, price impact) plus Token-2022 traps (transfer fee, transfer hook, permanent delegate, non-transferable, default-frozen) and mint/freeze authority. Base: honeypot/sell-tax/blacklist/owner-control flags plus DEX liquidity. Returns ve

$0.01 USDC required (x402 / Base or Solana) Paid 0.01 USDC, and only when there is something to deliver. Changes recorded across every member of a named set (inference or devtools) after your since cursor, newest first, each with the slug, detection time, source page and the same change object the per-slug endpoint returns. An empty window is answered free (charged false) and never reaches this p

Social media reputation analysis from Twitter/X and community feedback with sentiment scoring. Detect fake engagement patterns and measure trust indicators for reputation-based decisions. Price: $0.01 USDC

Converts one LLM tool/function definition (OpenAI, Anthropic, Gemini, MCP or plain JSON Schema; format auto-detected) into one or more target provider formats. Applies each provider's schema rules: OpenAI strict mode (all fields required, optional fields made nullable, additionalProperties false), Gemini's OpenAPI subset (no $ref, nullable, string enums), $ref inlining and name sanitising. Returns

HTTP endpoint health audit for one URL: status and redirect chain, latency p50/p95 over repeated samples, TLS certificate expiry and issuer, the response headers that matter, and a list of detected anomalies (missing HSTS/CSP/X-Content-Type-Options, expiring cert, weak TLS, CORS wildcard, insecure cookies, version disclosure, slow p95, redirect loops). Private, loopback and link-local targets are

Company enrichment from domain — composite domain dossier: RDAP registration + DNS infrastructure signals, tech-stack detection, likely corporate email patterns + MX verification, and SSL/TLS certificate health for one domain, fused into a single response with an aggregated signals list. Lead data for B2B prospecting. One domain per call. Tiger Operations. Use when vetting a company or domain and

Solana wallet profile: verdict (established/new/suspicious/inactive) with reasons from SOL balance, token holdings, wallet age (first tx), 24h/7d activity, program-account detection, bot-like pattern heuristic and OFAC sanctions match. Use when an agent is about to pay, airdrop to, trade with, trust or whitelist an unfamiliar Solana wallet. Not financial advice.

On-chain contract risk score: detects upgradeable proxies and privileged functions from live bytecode. Use before trading/interacting with an unfamiliar contract.

ERC-20 token safety pre-check from on-chain data only (Base, Ethereum, Arbitrum, Optimism, Polygon, BSC): name/symbol/decimals/supply, owner and whether renounced, EIP-1967/minimal proxy detection, and a bytecode scan (incl. implementation) for mint, blacklist, adjustable-fee, max-tx, trading-switch and pause functions, with flags and a risk level. Run before swapping into an unknown token. $0.005

Pre-flight due diligence for GitHub bounty issues. Detect competing PRs, stale issues, maintainer inactivity, saturation and payout-risk signals before an autonomous coding agent spends compute on implementation.

Detects the technology stack of any public website from one page load plus public DNS: CMS, ecommerce platform, JS framework, web server, CDN/hosting, analytics, ad pixels, chat, payments, consent, plus email provider, email-sending services, DNS host and verified SaaS (MX/NS/TXT). Each hit has categories, version when exposed, confidence 0-100 and evidence. 266 signatures.

Domain trust report for AI agents: is this domain real, how old is it, who registered it, and is its email locked down? DNS (A/AAAA/NS/MX/CAA), DNSSEC, SPF, DMARC, DKIM (common selectors), MTA-STS, TLS-RPT, BIMI, RDAP registration date + registrar + status, parking and disposable detection, risk flags, 0-100 score and verdict. Public DNS + RDAP, no data stored.

Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

An agent preparing a native HTML form reset needs missing required choice groups after radio ownership/name grouping and select placeholder/reset selection are combined, without user values or submitting anything.

Does a website use Beaver Builder? Fetches the page (homepage for a bare domain) and matches Beaver Builder's fingerprints in the HTML and response headers, returning yes/no with the evidence snippet and the category (page-builder). Technographics for sales, competitor research and migration planning, one technology per call. $0.01 per check.

Actionable Base DEX intelligence — newly created pools enriched with token metadata, stablecoin-based liquidity estimates, transparent heuristic risk flags, and a trade/watch/skip signal.