blogwatcher

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the CLI accepts arbitrary blog URLs (e.g., "blogwatcher add ... https://xkcd.com") and the "scan" command fetches RSS/Atom/blog content to list and read articles, meaning the agent ingests public, untrusted third‑party content that could contain instructions affecting subsequent actions.