generating-glossaries-and-definitions

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

• Third-party content exposure detected (high risk: 0.70). The skill's Step 1 instructs the agent to "Gather terms" from third-party sources such as "Competitor glossaries" and "Search queries" (and references public resources), which implies fetching and reading open/public web content that could be untrusted and user-generated as part of its workflow.