InjectScan
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.
injectscan.agentgate.workers.devBase
- Category
- Social & people
- Starting price
- $0.003
- Paid calls · 30 days
- 0
- Unique payers · 30 days
- —
Paid endpoints
1 endpoint, sorted by usage. Prices are per request.