gadd-next

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly reads external tracker state and issue/pr bodies (e.g., GitHub PR URLs and external tracker sync state recorded in the ledger) and uses that untrusted, user-generated content to decide next_command and next_human_action, so third-party pages can influence its workflow.