Quill

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

• Third-party content exposure detected (high risk: 0.70). The skill's required READ/SURVEY steps explicitly include "check broken links and stale references" and "link health" (SKILL.md), and the included references/coverage-audit-tools.md shows a Link Health Checker using markdown-link-check that fetches arbitrary external URLs (e.g., https://github.com) — meaning the agent will fetch and interpret public third-party pages as part of its workflow, which could allow indirect prompt injection.