cmd-rss-feed-generator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Step 2 "Analyze the Blog Source") and required functions like fetch_content(url) explicitly instruct the agent to fetch and parse arbitrary blog websites or HTML files from the public web, i.e., untrusted user-generated web content, and to use that content to drive how it generates scraper code and feed outputs—so third-party content is ingested and can materially influence the agent's actions.