temporal-applications-python

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

• Third-party content exposure detected (high risk: 0.80). The skill's resources (notably resources/activities.md and resources/workflows-continue-as-new.md) show activity examples that accept and fetch/parse arbitrary URLs (e.g., ReadCodesParams.url, read_codes(self.browser, params.url), parse_article) and workflows that extend their to_crawl list from processed results (ProcessArticleWorkflow.run → discovered URLs), meaning the agent is expected to ingest and act on untrusted public web content which can materially influence subsequent actions.