Niches · Security intelligence
Check a file or hash for malware verdicts
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
Per-engine detections with engine names and the analysis date, a statement when the hash is unknown, and no upload or sharing of the file unless the user asked.
How agents ask for it: is this file safe
, check this hash
, why is my binary flagged
Does the job, with a limit 1
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| VirusTotal BB Google LLC | v3 file reports give last_analysis_results per engine with last_analysis_date and 404 when unknown, without uploading; VTAI says submit only when asked. Public key is 4 a minute, VTAI drops engine names, and acc-23, acc-24, acc-25 show minority-engine flags with no false-positive signal. source |
Doesn't do this job 8
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| AbuseIPDB C AbuseIPDB LLC | No file or hash lookup; the API covers IP addresses and subnets only. source |
| Censys B Censys, Inc. | No file or malware hash lookup; the only SHA-256 it takes is a certificate fingerprint. source |
| GreyNoise B GreyNoise Intelligence, Inc. | No file or hash endpoint; it classifies IPs seen scanning. source |
| IPinfo B IPinfo Inc. | No file or hash lookup. source |
| Pulsedive D Pulsedive LLC | Indicator types are domain, ip and url only; no file or hash lookup. source |
| SecurityTrails F SecurityTrails (Recorded Future) | No file or hash endpoint. source |
| Shodan E Shodan (no company name on its pages; shodan.io is registered to John Matherly) | No file or malware hash lookup. source |
| WhoisXML API C Whois API, Inc. | The threat API matches a hash against its IoC data but has no per-engine detections or analysis date. source |
What stops agents finishing
- public key limited to non-commercial use and 4 lookups a minute
- uploading a private file shares it with partners
- a few engines flagging with no way to tell a false positive
Around it
Before: file-storage.read-file. After: code.open-issue, human-in-the-loop.approve-action.
Where this comes from
Weight 14 of 100 in Security intelligence: 5 of 41 accounts, all VirusTotal; three are false-positive worries about the user's own or a trusted binary
The same as data: /api/v1/use-cases/security-intelligence.file-hash-verdict.json, or the MCP tool get_use_case with id security-intelligence.file-hash-verdict. Other jobs in this category: /api/v1/niches?category=security-intelligence.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.