github-automation

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

• Third-party content exposure detected (medium risk: 0.30). [SKILL.md] specifies that at runtime the workflow will list/search, then read specific GitHub issues/pull requests (including comments and conversation text) from user-chosen items on GitHub before making changes, which is insider text submission by outsiders and thus exposes the agent to free text via GitHub issue/PR comments.