buy or bounce

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests the “asset to test” (including if it is a URL fetched at runtime or pasted outsider-authored text), and that fetched/pasted free-form prose is then read and summarized into the agent’s LLM context for analysis, which is an outsider source path.