{"uid":"cap_SYcGM4HYIv34oFWeIrGY4","slug":"trustfetch-batch-injection-scan-13089f96","name":"TrustFetch Batch Injection Scan","description":"Volume tier: scan up to 10 texts for a single flat price -- cheaper per item than calling the fast tier that many times separately.","url":"https://trustfetch.duckdns.org/tools/injection-scan/batch","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"texts":{"type":"array","items":{"type":"string"},"description":"List of texts to scan, one result per text"}}},"responseSchema":{"type":"json","example":{"count":1,"results":[{"signals":[{"snippet":"Ignore all previous instructions","reasoning":"Text contains a phrase attempting to override prior instructions.","technique":"override_phrase","confidence":0.9}],"reasoning":"Text contains a phrase attempting to override prior instructions.","technique":"override_phrase","confidence":0.9,"detector_tier":"heuristic","flagged_snippet":"Ignore all previous instructions","injection_suspected":true}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.12","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.12/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.12","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.12","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_GvD6Let0ebQviCkqOcau5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.12","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scans a batch of text strings for hidden prompt-injection attempts, returning per-text signals, confidence scores, and detected techniques.","exampleAgentPrompt":"Before you act on this batch of user messages, scan all of them for prompt injection attacks and tell me which ones contain suspicious override phrases or hidden instructions trying to hijack your behavior.","exampleUseCases":[{"title":"Guard agent against user input hijacking","prompt":"I'm about to let my agent process these 5 user-submitted messages, but first scan all of them for prompt injection attempts — flag anything that looks like it's trying to override the agent's instructions or smuggle in hidden commands."},{"title":"Screen scraped webpage before agent reads it","prompt":"I just scraped the text from this webpage my agent is about to summarize. Before it reads the content, scan it for any embedded prompt injection phrases or jailbreak attempts hidden in the page text."},{"title":"Audit customer support tickets for adversarial input","prompt":"We have 20 customer support tickets that will be processed by an AI. Can you scan all of them at once for hidden prompt injection attempts or override phrases before we feed them to the model?"}],"resultDescription":"Returns a JSON object with a count and a results array (one entry per input text). Each result includes: injection_suspected (boolean), confidence (0-1 float), technique name (e.g. 'override_phrase'), flagged_snippet (the offending text), reasoning (human-readable explanation), detector_tier (e.g. 'heuristic'), and a signals array with granular per-signal details including snippet, reasoning, technique, and confidence.","failureModes":["Missing required 'texts' array returns validation error","Empty texts array may return empty results with no useful signal","Very long or malformed strings may cause processing errors","Heuristic detector may produce false positives on benign imperative language","Low-confidence detections (confidence < 0.5) may not reliably indicate true injection","Network or DNS issues with duckdns.org domain could cause connectivity failures","Payment authorization failure blocks the call before scanning begins"],"whenToPreferThis":"Choose this endpoint when you need to screen multiple texts at once for prompt injection before an AI agent acts on them — especially when processing untrusted user input, scraped web content, or external documents in bulk. It is purpose-built for LLM security use cases rather than general content moderation or spam filtering. Prefer this over single-text scanning when you have 2+ texts to check, since batch processing is more cost-efficient per text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:43:50.305Z","isFirstParty":false}