45 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Current weather at a place: temperature (°C), humidity (%), pressure (hPa) and wind (m/s) from the nearest live Open-Meteo relay within 75 km, with a signed receipt. Send latitude and longitude, or a city.
Check an email or web page for text a person reading it would not see but an AI reading it would: HTML comments, display:none or hidden elements, white-on-white or off-screen text, zero-width and tag characters, base64 t...
Read one email the way an agent that triages mail should before acting on it: observations with evidence and offsets, no score and no verdict. Send the raw RFC 5322 message (multipart, base64 and quoted-printable decoded...
Generate speech in 41 voices and 6 languages as MP3, WAV or Ogg audio. Use when an agent must turn text into spoken audio in English, Spanish, French, Hindi, Italian or Portuguese.
Prompt injection detection and content moderation for AI agents: flags hidden instructions aimed at an LLM (none / suspicious / malicious + score) and harmful content (hate, violence, sexual, harassment, self-harm, illeg...
Prompt-injection and manipulation scan for untrusted text, HTML, email, and tool output.
Scan a file's metadata for privacy risks. Pay 0.002 USDC per call. Results are signals, not verdicts.
Scan a file's metadata for privacy risks. Pay 0.002 USDC per call. Results are signals, not verdicts.
Deterministic static prompt-injection scan of any prompt, tool description or MCP manifest.
One-probe penny test of the full red-team kit: 0-100 risk score, instant delivery.
Scan untrusted text for common prompt-injection and instruction-override patterns
Prompt injection detection for AI agents: check untrusted text (a web page, email, tool result or user message) before your agent reads it. Returns a verdict safe, suspicious or malicious, a 0 to 100 risk score, the tech...
Prompt injection detection - screen text, a web page or tool output for block, review or allow with a risk score
Detect language, formality and tone of a text with confidence scores. Deterministic heuristics + compact wordlists. Returns iso_639-1 + register. — $0.001 USDC/call on eip155:8453. Pay-per-call via x402 — no API key, no...
Bulk company lookup: run one tool (tech stack, open jobs, hiring intent, Google Ads or company profile) on many domains with one payment. Step 1 (free): send {tool, domains}; every domain is checked and you get each stat...
Scan untrusted tool or web responses for prompt-injection and credential/payment exfiltration patterns; return findings plus sanitized content.
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 attr...
Static security scan of a single text or prompt blob: hidden unicode, prompt injection, data-exfiltration directives, dangerous-capability and tool-shadowing language, and obfuscation. Returns a 0-100 risk score, categor...
Static security scan of an MCP manifest or tool list. Detects tool poisoning, hidden unicode instructions, prompt injection, data-exfiltration directives, dangerous capabilities, tool shadowing and post-approval rug-pull...
Deterministic LLM red-team scan: prompt injection, jailbreak, system-prompt extraction and MCP tool abuse in agent prompts.
prompt-injection risk scan: detects instruction override, tool abuse and secret exfiltration phrases before an agent consumes untrusted text.