github

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow (references/stacked-pr-workflow.md and SKILL.md) explicitly instructs using the gh CLI to fetch and read GitHub PR details—user-generated content on GitHub.com—which the agent must interpret and that can influence subsequent git/gh actions, exposing it to untrusted third-party instructions.