read-rss-aggregator

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

• Third-party content exposure detected (high risk: 0.85). The required workflow runs scripts/aggregate.py, which fetches RSS feeds from outsider-controlled public URLs listed in references/feeds.opml and extracts their summary/description text (cleaned but still free text) into the script’s output—this is the kind of outsider-authored prose that can be ingested into the agent’s LLM context when the agent relays the results.