personal-assistant

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md's "5. Recherche d'Informations et Synthèse" workflow explicitly instructs the agent to use google_web_search and web_fetch to find and read content from public web articles, which are untrusted third-party sources that the agent will interpret and use to influence its outputs.