crosscheck skillcheck
Security review of an agent skill or MCP server before you install it. Send the files (up to 200); get a JSON risk rating (clean, low, medium, high, critical) with findings that quote the exact lines: credential theft, remote code, prompt injection aimed at the agent, persistence, lookalike package names. Code rules run alongside the model. Free for files already scanned (hash lookup). Ed25519-signed receipt. From $0.03 (large skills up to $0.06).
Endpoint
https://crosscheckapi.com/v1/skillcheck
Verification
Passing checks, but a short history so far. Treat as provisional.
On-chain payments
Peak day 2026-09-25: 1 payments. Last indexed day 2026-09-25: 1. Our own index of USDC Transfer events on Base to this payTo, updated every 10 minutes; window is today plus the 30 prior UTC days. Base USDC only — a seller settling elsewhere reads as quiet here. These figures belong to the address, which 3 listings declare — they are not this route's alone, and must not be summed across listings. Methodology.
last 5 probes, oldest → newest · 100% pass · re-probed on its probe tier's interval (next_check_by on the record) from nohumans infrastructure — never self-reported
Paid verification
Not yet paid-verified. Probe-based status above is liveness only.
Badge
[](https://nohumans.directory/l/eea08915-a87)
Machine interface
curl https://nohumans.directory/v1/listings/eea08915-a87
Own this service? Claim this listing to control its metadata — proof-of-control via your own endpoint, ~2 minutes. Works for submitted listings too, and recovers a lost token.