ce-work

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

• Third-party content exposure detected (high risk: 0.80). The skill's required Phase 1 "Read Plan and Clarify" step explicitly instructs the agent to "review any references or links provided in the plan" (and the workflow also references external integrations like ce-figma-design-sync and tracker detection that probe GitHub/Linear), which means the agent will fetch and interpret arbitrary external/user-provided links, designs, or tracker content that can materially influence execution decisions.