connecting-agents-across-machines

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch instructions from an external URL (curl -sSL -H 'Accept: text/markdown' https://arelay.to/agent-relay), which is a low-risk user/fetched content source.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading instructions from an unverified external domain via curl during setup, constituting a high-risk unverifiable runtime external dependency.