geolocation-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow explicitly requires performing web searches and verifying hypotheses against open/public sources (see "Web Search Verification" in SKILL.md and reference/verification-strategies.md, which direct checking Street View/Maps, local news, and user-generated sites), so the agent will ingest untrusted third-party content that can influence its decisions and actions.