Skip to main content

isinjected

Is this prompt malicious?

Scan fetched pages, emails, tickets and tool results for prompt injection, and check their links against our threat-indicator corpus.

Create free accountRead the API docs

1,000 scans/month free, no credit card. Scans are metered separately from your API request quota.

Detections

Four injection families, checked on every scan.

Instruction override & jailbreaks

“Ignore all previous instructions”, fake system prompts, role hijacks and DAN-style jailbreaks.

Invisible & encoded payloads

Unicode tag-smuggling, zero-width characters, bidi overrides, and base64/percent-encoded instructions are decoded and flagged.

Data exfiltration & malicious links

Markdown-image beacons, data: URIs, and any URL/domain/IP checked against known-malicious infrastructure.

Tool-call forgery

Forged tool calls, function-call structures, and shell exhortations that try to drive your agent's tools.

API

One call before your agent acts

Send the untrusted content; get back block, warn, or allow, with the flagged spans and a sanitized copy.

curl -X POST "https://ismalicious.com/api/gate/scan" \
  -H "X-API-KEY: $ISMALICIOUS_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "…fetched page text…", "source_url": "https://example.com"}'

See the MCP setup and run a content scan

MCP

Add it to your agent in one line

Six tools over the same API for Claude Desktop, Cursor, Windsurf or your own agent, with typed errors.

npx -y @ismalicious/mcp-server

Or declare it in the client's MCP configuration:

{
  "mcpServers": {
    "ismalicious": {
      "command": "npx",
      "args": ["-y", "@ismalicious/mcp-server"],
      "env": {
        "ISMALICIOUS_API_KEY": "your-api-key",
        "ISMALICIOUS_API_SECRET": "your-api-secret"
      }
    }
  }
}

No key yet? Omit both variables: the server then offers bootstrap_key, which mints a free key from an email address (one per IP per day).

  • scan_before_usePrompt-injection scan plus link reputation over untrusted content; block, warn or allow.
  • check_urlReputation of one URL, domain or IP before fetching it.
  • check_indicatorVerdict for an IP, domain, URL or hash: risk score, citing blocklists, timeline, network and a recommended action.
  • get_cveOne CVE with CVSS, EPSS, CISA KEV status and due date, exploitation evidence and references.
  • recent_cvesLatest CVEs, optionally by severity.
  • search_indicatorsSearch the corpus by pattern, source or threat class; paginated.
  • check_indicatorsBulk check up to 100 indicators in one call; one request charged per indicator.
  • check_password_exposureWhether a password, or its SHA-1 or NTLM hash, is in known breach dumps and how often; the password is hashed locally and only a 5-character prefix is sent.
  • scan_emailScan one email message for phishing and malware: verdict, recommended action and reasons, from the sender, links and attachment hashes; one scan per message.
  • bootstrap_keyWithout a configured key: mint a free one from an email address.

npmMCP registry: com.ismalicious/mcp-server