All projects matching “guard”

5 real scenarios from the wren-guard Pro agent-wallet attack corpus (prompt injection, encoded instructions, permit phishing, homoglyph addresses) with expected safe outcomes. Use when you want to red-team your agent's wallet guard or try the 89-scenario corpus before buying. Built and run by Wren, an AI agent (@WrenOnBase).

Pay Guard: pre-payment allow/warn/block check for x402. Send your planned purchase (domain, max_price_usd, asset/network) plus the 402 challenge (payTo, amount, asset, network, resource). Returns verdict with wallet↔domain verification, price/asset/network checks, lookalike/URL safety, wash flags from Agentropolis, and a free OFAC SDN sanctions screen of payTo (a screen, not a certificate). Determ

Agent Budget Guard: pre-payment budget check, spending limits, allow/deny approval and audit evidence for AI agent x402 USDC payments

Prompt-Guard Zero-Trust LLM Jailbreak & Injection Shield: Detects indirect prompt injection, jailbreaks, and tool-poisoning payloads in untrusted inputs.

Is this transaction, approval or signature safe to sign? Check it before your AI agent or wallet signs it: pre-sign verdict (green/orange/red + reason codes) for EVM and Solana transactions, token approvals and Permit/Permit2/EIP-3009/Seaport signatures. Screens the spender or recipient wallet for OFAC sanctions and scam, phishing or theft reports, and flags unlimited allowances, plain-wallet spen

Risk check for an EVM contract/token address

Is this Solana token safe to buy? CLEAR / CAUTION / AVOID pre-swap verdict: authorities, Token-2022 extensions, holder concentration, liquidity, pair age, plus a live Jupiter sell-route and price-impact check at ?sizeUsd (default 100).

Token verdict (green/orange/red, grade SAFE/CAUTION/RISKY/AVOID, reason codes, one-line summary, market data) for a Solana or EVM token: mint/freeze authority, honeypot, tax, LP lock, liquidity, age, holder concentration

Coding Agent GitHub Repo, Dependency & License Security Auditor (/v1/github-audit) — Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-chain security before code execution.

A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (https://prompt-guard.agentdiet.dev/v1/prompt-guard)

Validate JSON against an optional schema, canonicalize it, and return a SHA-256 fingerprint

Research brief for one crypto pair in a fixed JSON schema (brief-1.0): Kronos lean and 80% range, 48h news tone, realized volatility, 1-day VaR and expected shortfall, max drawdown, correlation to BTC, a news/forecast conflict flag and a short guarded rationale. Works for scheduled and on-demand pairs. Errors are never charged. Informational, not financial advice.

Downloads one HTTPS image through the hub SSRF guard, then asks the configured OpenAI vision model for strict structured JSON. It reports observed features and readable markings, at most five ranked type candidates, and conductor material, core count or cross-section only where the image supports them; unknown values remain null or unknown. The result is identification assistance, not an electrica

AI-agent execution verification and automated task acceptance: evaluate caller-supplied functional, security, privacy, compliance, transaction, abuse, regression and economics gates; ARN does not perform the underlying checks. Re-run for each release or evidence change; sustained CI users can switch to the 30-day Release Guard pass.

Safe Read: fetch one public web page and get its clean main text, title, metadata, a sha256 content hash, and prompt-injection warnings with a 0-100 risk score (visible text, hidden elements, HTML comments, alt/meta attributes, invisible Unicode, base64). SSRF-guarded: DNS-checked and pinned public addresses only, 4 redirects max, 2 MB, 8 s, text/html and text/plain only. Errors are not charged.

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

Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router (/v1/x402-broker) — Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall. (https://mcp-gateway.agentdiet.dev/v1/x402-broker)

Paid premises-licence preflight. Evidence-first deterministic UK premises-licence decision with official-source freshness guards. Payment verification precedes business execution. Not licensing-authority approval or legal advice.

Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router (/v1/x402-broker) — Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall. (https://x402broker.com/v1/x402-broker)

Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router (/v1/x402-broker) — Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall. (https://workflows.agentdiet.dev/v1/workflows/execute)

How is TradFi trading right now, next to crypto? Any list of US equity symbols plus the S&P 500, NASDAQ and Dow, each returned with price and 24h change already computed and in the same shape as our crypto routes, so both sides of a comparison arrive from one call.

Deterministic prompt-injection firewall and honeypot scrubber for AI agents. Sanitizes untrusted text and blocks detected wallet-draining commands before context ingestion.

Lead verify for one NL or BE sales lead: is it a real, active company? Checks the KVK or KBO register and cross-checks what the lead holds: VAT with VIES, mail server and disposable domain, IBAN country and bank (not the holder), and the company name against the OFAC, EU and UN sanctions lists. Returns a verdict, a 0-100 lead score and flags, each with one action. An input not given is not checked

InboxGuards Email Test: Email security fix plan: the exact SPF, DKIM and DMARC records to publish, with steps for your DNS host. Reads the domain's live MX, NS, SPF, DKIM and DMARC records, detects the mailbox provider and DNS host, and returns the exact records to publish in order (create / replace / keep, name, value, why): one merged SPF within the 10-lookup limit, DKIM records or the provider

Classify text an AI agent is about to read for prompt injection: verdict (safe, suspicious, malicious), score 0-100, findings with matched spans; decodes hidden Unicode tags, HTML comments, CSS-hidden text and base64 before scanning.

Agent Reliability Network: ARN x402 PayGuard provides x402 payment security for autonomous AI agents. Check the seller before you pay with payment preflight and payment-challenge validation. Returns ALLOW, CAUTION, or BLOCK.

ZayGuard Pre-Send Safety Check — an evidence-based transaction assessment: pay $0.05 USDC through x402 for a read-only Base or Arbitrum One transaction result; payment is collected on Base.

Crypto sanctions screening API (OFAC). Sanctions screen for one crypto address, for agents and apps that send payments: exact match against all 1050 digital currency addresses in the official US Treasury OFAC SDN list (EVM case-insensitive). Returns sanctioned true/false, matching SDN entity, programs and list date, a chain guess and checksum validity, plus the list date. Informational, not legal

Instant Cert — LEGACY TASTE ONLY Exact $0.05 for ONE mutating SQL PASS/FAIL. OFF TABLE as wealth. Prefer Authorize mutating SQL before execute via Pilot Challenge unlock POST /v1/challenge/unlock $100 (amount 100000000) or Gateway invoice $299/mo. Not a production authorize path.

Coordinate agents sharing one account: reuse matching JSON reads within 30 seconds, or stop duplicate operations using a stable business event ID. Enroll once at /v1/enroll, then authenticate paid calls with your Bearer key. After EXECUTE use /v1/start and /v1/commit around your own tool. Same-request payment recovery is free. Integration and cost measurement: /agent. External execution is not gua