Self-service

Commission a skill code audit

We download the exact published version of the skill from the ClawHub registry, read every file statically (nothing is executed), and publish what the code does: network destinations, binaries, credentials it reads, wallets, obfuscation, download-and-execute, instructions that try to steer the agent, with file and line for every finding, and a verdict: SAFE, CAUTION or UNSAFE.

The result is published whatever it says, at /k/<slug>.audit, with a JSON and a badge. Anyone can commission it: the author, a user, a platform. It does not change the skill's trust tier. No refunds. The author may respond through the dispute channel, and the response is published with the audit. A new version of the skill invalidates the audit; re-audit at the same price.

Skill slug (as on clawhub.ai)

Scripts and agents: GET https://agenteconomy.report/api/audit/<slug> with any x402 client; status at GET https://agenteconomy.report/api/audit/<slug>/status. The audit runs within about 15 minutes of payment.