research

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

• Third-party content exposure detected (high risk: 1.00). This skill's Research workflow explicitly instructs performing web searches and cloning/examining GitHub repositories (e.g., "Web Search First" and the git clone commands in SKILL.md), meaning it ingests untrusted public third-party content that it is expected to read and use to drive recommendations and next actions.