opendeploy-setup

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow includes fetching/reading the official start page when the user requests it (“Read https://opendeploy.dev/start”), which is public web content authored by an outsider and can be ingested as free-form text into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes an explicit runtime install command that downloads and executes remote code: "curl -fsSL https://raw.githubusercontent.com/opendeploy-dev/opendeploy-opencode/main/install.sh | bash", which fetches and pipes a remote script to a shell.