paperclip-create-agent

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the curl utility to interact with the Paperclip API. These commands are used for identity verification, retrieving configuration templates, and submitting JSON payloads for agent hiring requests.
  • [EXTERNAL_DOWNLOADS]: Fetches text-based configuration data and metadata (such as icons and adapter settings) from the Paperclip API to inform the agent creation process.
  • [SAFE]: Authentication is correctly handled using environment variables (PAPERCLIP_API_KEY) provided by the host environment, avoiding hardcoded secrets.
  • [SAFE]: References to external components, such as the browser skill from Vercel Labs, involve well-known and trusted organizations and are used solely as configuration parameters for newly created agents.
  • [SAFE]: The skill implements a governance-aware workflow that includes permission checks, draft reviews against a checklist, and an approval lifecycle for agent creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 11:20 PM