setting-up-capy-on-agent-relay

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing an MCP plugin from the vendor's repository on GitHub. This is a standard and documented part of the Agent Relay setup process.
  • [CREDENTIALS_UNSAFE]: The instructions guide the user to handle API keys securely by using the designated settings UI and explicitly warning against sharing credentials in the chat.
  • [INDIRECT_PROMPT_INJECTION]: By enabling message relaying from external agents, the skill introduces a surface for indirect instructions. However, this is inherent to the relay's purpose, and no specific exploits or unsafe handling of this data were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:10 AM