jev-search-and-rerank

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

• Third-party content exposure detected (medium risk: 0.30). The workflow performs public conversation discovery and search retrieval, ingesting external public posts and search results which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation from an explicit GitHub-style repository locator (fellowship-dev/dogfooded-skills), which is an unofficial third-party source providing runtime companion code (jev-evidence) executed by the skill.