mrt-rerouter-skill

Warn

Audited by Snyk on Jun 25, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). At runtime, the skill calls public/outsider-authored HTTP APIs (e.g., LTA traffic images, NEA PSI/weather, LTA bus arrival) via singapore_api.request_json() inside assess(), and then ingests their JSON fields (free-text like NEA forecast strings) into the LLM context through the returned result object.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 04:52 AM
Issues
1
Security Audit — snyk — mrt-rerouter-skill