metascraper

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow (see "Getting HTML" in SKILL.md) explicitly instructs fetching/ingesting HTML from target URLs or using the local html-get skill or Microlink API, meaning it consumes open/public web pages (untrusted third-party content) that the agent must parse and which can influence downstream actions.