logvalet-report

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches Backlog user-generated data (e.g., via "lv user activity USER_ID ... -f json" in Step 4 and "lv project get PROJ -f json" in the Important rules/Step 5) and parses that content to aggregate results and drive follow-up queries, so untrusted third-party content can influence tool calls and report generation.