smart-commuter-skill

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

• Third-party content exposure detected (high risk: 0.85). At runtime the agent calls this skill’s script, which fetches public free-text fields from outsider-authored sources via data.gov.sg/OneMap APIs (e.g., NEA forecast items[].forecasts[].forecast and LTA camera name), and then injects those strings into the LLM-visible JSON response (including recommendation).