use-arc

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 read external documentation links like https://docs.arc.network/llms.txt, but web pages fetched on demand represent low indirect prompt injection risk.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill includes a shell command fetching and executing a remote installation script from foundry.paradigm.xyz, which constitutes an unofficial operational dependency.