project

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text from arbitrary GitHub repository contents when users run /project learn (and related commands that scan/index), because scripts/learn.ts/scripts/reunion.ts clone external repos via ghq get and then later enumerate/read .md files from those clones for manifest/indexing.