Screens one text for prompt-injection patterns in English (instruction override, role or system-prompt extraction, jailbreak personas, hidden or encoded instructions) using a fixed rule list based on OWASP LLM01 categories. Returns HIGH/MEDIUM/LOW/NONE, each match, and the text with matches removed. A rule list misses rewording and other languages: treat NONE as no known pattern, not as safe.
| Network | Scheme | Amount | Pay To |
|---|---|---|---|
| Base | exact | $0.002000 USDC | 0xb849...eAfA |
| solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp | exact | 0.00 tokens | J8vnmB...RdhR |
| eip155:5042 | exact | 0.00 tokens | 0xa475...9be3 |
| Polygon | exact | $0.002000 USDC | 0xb849...eAfA |
| Arbitrum One | exact | $0.002000 USDC | 0xb849...eAfA |
| eip155:143 | exact | 0.00 tokens | 0xb849...eAfA |
| eip155:480 | exact | 0.00 tokens | 0xb849...eAfA |
| Optimism | exact | $0.002000 USDC | 0xb849...eAfA |
| Celo | exact | 0.00 tokens | 0xb849...eAfA |
| stellar:pubnet | exact | 0.02 tokens | GBIX2M...OAFI |
| xrpl:0 | exact | 0.002 | rDxNZC...f8UJ |
| xrpl:0 | exact | 0.00 tokens | rDxNZC...f8UJ |