cogni-issues

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow includes fetching and parsing GitHub issue bodies/comments via scripts/gh-issues-helper.sh view (and related list/search) which calls gh issue view and returns outsider-authored free text (issue/PR content and comments) to the skill for summarization/status.