startup-validator

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow instructs the agent to perform web searches and then use web_fetch to read full articles from sources like Gartner/McKinsey/Statista/Crunchbase, which means outsider-authored text from arbitrary webpages can be ingested after the user provides an idea that drives the search keywords.