plugin-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly accepts a "source URL/path" and includes commands like "inspect-source " and a "convert" mode (see SKILL.md and the conversion references that cite GitHub repos such as agenticnotetaking/arscontexta), so it ingests and interprets arbitrary public third‑party repository content during conversion which can materially influence packaging, validation, and follow-up actions.