marketplace-structure

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

• Third-party content exposure detected (high risk: 1.00). The skill documents adding and curating plugins from public GitHub/GitLab/other git URLs (e.g., "plugin marketplace add owner/repo", "plugin marketplace add https://gitlab.com/... .git", and the examples/community-marketplace.md community marketplace) and describes fetching plugin code/metadata from those external repositories, meaning the agent will read and interpret untrusted, user-authored third-party content as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly shows runtime git sources (e.g., https://gitlab.com/team/plugin.git) that are fetched when adding/updating marketplaces and those fetched plugins can include agent files, hooks, or command binaries that control prompts or execute code, so this is a runtime external dependency that can directly control behavior.