timesheet

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

• Third-party content exposure detected (high risk: 0.75). The skill is a CLI wrapper around timesheet.io and its runtime workflow necessarily ingests outsider-authored free text from the service’s API responses (e.g., task/project/absence/todo/note descriptions and other user-entered fields) into the agent’s LLM context when the agent reads --json output.