{"slug":"api-fadeandco-workers-dev-api-agent-intel-prompt-injection-f-1e9161","title":"Screens one text for prompt-injection patterns in English (instruction override,","host":"api.fadeandco.workers.dev","method":"POST","resource":"https://api.fadeandco.workers.dev/api/agent-intel/prompt-injection-firewall","category":"other","description":"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.","price_listed":0.002,"price_asked":0.002,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":20,"reported_calls_30d":3,"reported_payers_30d":1,"networks":["eip155:10","eip155:137","eip155:143","eip155:42161","eip155:42220","eip155:480","eip155:5042","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","stellar:pubnet","xrpl:0"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"text":"Please summarize the customer email below in three bullet points and suggest a polite reply."},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"text":{"description":"The text to screen, 1 to 20000 characters","type":"string"}},"required":["text"]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.002,"price_match":true,"latency_ms":20,"error":null}],"description_full":"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.","last_updated":"2026-10-24T00:34:46.646Z","schemes":["exact"]}