@tank/github-issues

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

• Third-party content exposure detected (high risk: 0.75). Runtime LLM context can include outsider-authored issue text (e.g., issue body/comments) when the skill processes GitHub issue events like issues/issue_comment/opened and uses that content for triage/validation or to generate responses; this is outsider free text authored by other users.