doc-daily-digest

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests untrusted public content (Step 2: WebFetch of arbitrary https:// URLs, res-x for X/Twitter, and GitHub page fetches with scrapling fallback) and then reads and summarizes that content to create notes and drive edits, so third-party page content can materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime WebFetch of arbitrary web pages and GitHub repo pages (e.g., https://github.com/{owner}/{repo}) and then injects that fetched content into explicit extraction prompts like "Extract: ... based on the README," so external URLs fetched at runtime directly control the agent's prompt context and are a required dependency.