github-profile-beautifier

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

• Third-party content exposure detected (high risk: 0.75). The skill fetches GitHub user/repo data at runtime via gh api users/$USERNAME and gh repo list $USERNAME ... --json ..., then interpolates fields like bio and description into the generated README template, so outsider-authored free text from the target user’s GitHub profile/repositories flows into the agent/LLM context for templating.