git-workflow-ps-tech

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read GitHub state and PR metadata using the GitHub CLI (see SKILL.md "Read GitHub state with gh" and reference.md commands like gh pr view ... --json), which fetches user-generated, public content that the agent will interpret to decide git/PR actions—exposing it to untrusted third-party input.