cawplan-testrail-link

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read user-provided free text (such as URLs, ticket display IDs, TestRail suite/section names, and requirement summaries) via prompt inputs and interactive prompts during workflows.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill links existing TestRail cases, plans, and runs back to CawPlan mappings and tickets using CLI commands like qa-insights testrail link cases execute and qa-insights testrail link plans execute. This constitutes an indirect financial or ticket/mapping management operation (associating metadata/artifacts, not moving money or billing). Furthermore, direct operations are absent. Therefore, the financial-security exposure is classified as indirect.