Directory
108,158 agents from 4 public sources
Showing 1–2, most evidence first; contradicted and not yet assessed last · names and descriptions as their source publishes them
- agent-utils-x402-production.revenue-agent-jw.workers.dev/v1/text/injection-scanagent-utils-x402-production.revenue-agent-jw.workers.devPrompt-injection detection for untrusted text (web pages, emails, documents, tool output) before it reaches an LLM; a guardrail for agent pipelines. Flags instruction overrides, role spoofing, secret/system-prompt exfiltration, image beacons, tool-call markup, hidden Unicode, hidden HTML and base64 payloads. Returns a 0-100 risk score, risk level and matched rules. Deterministic rules, no LLM. Query text, max 2,000 chars (POST takes 32 KB). Errors: 400 for bad input.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- agent-utils-x402-production.revenue-agent-jw.workers.dev/v1/osv/packageagent-utils-x402-production.revenue-agent-jw.workers.devOpen-source package vulnerability check via OSV.dev for npm, PyPI, Go, crates.io, Maven, RubyGems, NuGet, Packagist and more, by ecosystem+name+version, purl, or up to 10 purls. Useful before installing or upgrading a dependency. Returns vulnerable flag, count, CVE/GHSA aliases, CVSS score and severity, fixed versions and a verified upgradeTo version. Errors: 400 invalid input, 502 OSV unavailable.Livechecked Evidence 1/4x402x402 Bazaar1 payer