{"uid":"cap_dkz5chaJmRn33W4KpZ5DL","slug":"trollbridge-caveat-check-f31d662b","name":"TrollBridge Caveat Check","description":"The insurance booth for AI agents, with Mini's Agent Supply Store on the side of the road. One hundred checkpoints: pre-transaction safety lanes (honeypot, approval-risk, rug-score, receipt-check, tx-dryrun, permit-scan, airdrop-verdict, deployer-history, wallet-watch, secret-scan at $0.02 USDC per call; the protection tier — /contract-check, /approval-screen, /tx-plain-english, /honeypot-check, /tx-simulate, /redteam, /skill-scan, /verdict, /egress-audit, /tool-gate, /airlock, /repo-scan, /prove, /task-scope — at $0.10; the one-call /shield don't-get-rugged screen at $0.25; the full /preflight bundle at $0.05), bounty intel (bounties, fresh, verdicts, deadlines, sweepstakes, opportunities) at $0.02 USDC per call, trader intel (/prices and /quant at $0.02; /enrich and /token-check at $0.05; /contract-check and /honeypot-check at $0.10; /sec-facts at $0.05), market intel (/markets and /search at $0.05; /grants at $0.02), DeFi intel (/yields and /new-pairs at $0.05; /gas and /defi at $0.02), AI intel (/models at $0.02), agent-ops intel (/prompt-cost, /model-picks, /rpc-speed, /terms-tldr, /scrape, /gigs, /retry-verify, /idempotency, /verify-independent at $0.02; /site-watch, /wallet-check, /code-run, /regulatory-pack, /sage, /cron-watch, /caveat-check, /tripwire, /escrow, /trust, /bridge-fees, /dao-votes, /dev-activity, /dex-arb, /dydx-perps, /funding-rates, /gas-predict, /hack-tracker, /long-short-ratio, /lp-yields, /mev-scan, /open-interest, /perp-basis, /polymarket-odds, /rwa-watch, /sentiment, /stablecoin-flows, /tokenomics, /top-movers, /whale-watch, and /yield-stable at $0.05; /approval-screen, /tx-plain-english, /tx-simulate, and /task-scope at $0.10; /scam-scan deep scan at $5.00 or 30-day subscription at $30.00), supply store (/road-pack combo meal at $0.05; curated datasets, the /audit-prep pre-audit review, and the /prove-state symbolic-execution run at $1.00; the /audit AI-agent audit at $25.00). Every lane answers before money moves — heuristic verdicts, not audits. Don't get rugged.","url":"https://mini-tollbooth.onrender.com/caveat-check?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["finding","source"],"properties":{"source":{"type":"string","description":"The original source text (text only — no URL fetching)."},"finding":{"type":"string","description":"The summary/claim text to check for dropped caveats."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"lane":"/caveat-check","summary":"…","verdict":"caveats-dropped","description":"NOT AN AUDIT — heuristic screen: paste a finding plus its source text (text only, no URL fetching) and get the dropped caveats flagged — numbers missing a baseline, claims missing a measurer, results missing conditions or versions — quoting the exact claim text ($0.05).","caveats_dropped":2,"claims_analyzed":3,"missing_caveats":[{"type":"missing-baseline","claim":"Model X is 30x faster.","what_to_ask":"Ask: compared to what baseline?"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_aflcfRga9ZfVWP4UjohQh","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyzes a claim or finding against its source text to identify dropped caveats such as missing baselines, missing measurers, or unstated conditions","exampleAgentPrompt":"Check this benchmark claim for dropped caveats — the finding is 'Model X is 30x faster than competitors' and the source text is the original paper abstract that says it was tested on a single H100 GPU with batch size 1 under specific temperature conditions. Flag anything missing like baseline, measurer, or version info.","exampleUseCases":[{"title":"AI benchmark claim integrity check","prompt":"I saw a tweet saying 'Our model scores 95% on MMLU, outperforming GPT-4' — the source blog post says it was tested with 5-shot prompting on a subset of 200 questions. Can you check what caveats were dropped from the tweet claim?"},{"title":"Research summary caveat audit","prompt":"This press release says 'Drug X reduces symptoms by 40%' but the actual study abstract mentions it was compared to placebo in a 12-week trial on 50 patients aged 18-30. Flag any missing caveats the press release dropped."},{"title":"Agent-generated output fact-checking","prompt":"My agent summarized a DeFi protocol audit as 'contract is safe and fully audited' but the original finding said 'no critical issues found in the ERC-20 transfer functions reviewed on version 1.2, oracle logic excluded.' What caveats got dropped?"}],"resultDescription":"Returns a JSON object with a verdict (e.g. 'caveats-dropped'), a summary, the number of claims analyzed, the number of caveats dropped, and a list of specific missing caveats each tagged by type (e.g. missing-baseline, missing-measurer, missing-condition) with the exact claim text and a suggested follow-up question.","failureModes":["Missing required 'finding' or 'source' query parameters returns an error","Source text is a URL rather than pasted text — endpoint does not fetch URLs, only processes plain text","Finding and source text are too similar or identical, yielding zero flagged caveats","Very short or vague source text may produce low-confidence or incomplete caveat detection","Payment not provided or insufficient USDC balance triggers x402 payment required response"],"whenToPreferThis":"Choose this endpoint when you need to programmatically check whether a claim, summary, or headline has dropped important caveats relative to its original source text — especially for AI benchmark results, research summaries, DeFi audit findings, or any context where numerical claims or performance results may be missing baselines, measurers, versions, or conditions. Prefer this over general fact-checking endpoints when the source text is already available and you need structured, typed caveat detection rather than a binary true/false verdict.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:47:53.300Z","isFirstParty":false,"canonicalSlug":"trollbridge-caveat-check-f31d662b"}