baoyu-post-to-x

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads remote images referenced in Markdown (see references/articles.md "Remote Images: Automatically downloaded to temp directory" and scripts/md-to-html.ts's downloadFile/resolveImagePath), parses Markdown to HTML, and uses that parsed content (titles, placeholders, image paths) to drive browser actions and image insertion—so it fetches and ingests untrusted public web content that can materially affect runtime actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly runs commands like "npx -y bun ..." at runtime (seen throughout SKILL.md and scripts), which will fetch and execute the bun package from the npm registry (e.g. https://registry.npmjs.org) — this is a runtime fetch of remote code that the skill can rely on and will execute.