openchoreo-setup

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

• Third-party content exposure detected (low risk: 0.10). The agent skill fetches and ingests documentation pages and markdown files from openchoreo.dev and GitHub repositories (github.com/openchoreo/openchoreo, community module repositories) via shell scripts (fetch-page.sh, git clone, curl), representing third-party documentation and package registries where the agent actively searches and fetches outsider-referenced URLs/content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script scripts/fetch-page.sh dynamically fetches LLM indices and installation guide pages from openchoreo.dev and GitHub raw content at runtime, constituting a common unofficial operational dependency.