python-executor

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly enables and demonstrates fetching and scraping public websites (e.g., examples using requests.get("https://example.com") and api.github.com) and lists web-scraping libraries (requests, BeautifulSoup, Selenium, Playwright) and "Web scraping" as a use case, so the agent can ingest untrusted third‑party content that could contain instructions influencing subsequent actions.