kspec-triage

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow (“kspec session start --full”, “kspec inbox list”, “kspec meta observations --pending-resolution”, “kspec tasks assess automation”, then “kspec triage start/record/act”) ingests the contents of inbox/observation/task items into the agent’s LLM context; those items are outsider-authored free text when they originate from external sources (e.g., public web content, third-party messages/comments, or other users’ issues/PRs/wiki text) rather than the operating user.