content-research-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Conduct Research" and "Research and add citations" steps (and examples referencing sources like the Stack Overflow Developer Survey and public studies) explicitly instruct the agent to search for, fetch, and extract information from external/open public sources, meaning it will read untrusted third-party (including user-generated) content as part of its workflow and could be exposed to indirect prompt injection.