remote-project-control

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and references/operations.md) explicitly runs networked commands like gh, git fetch/push/pull, ssh, and curl to inspect GitHub/GitLab repos, remote servers, and logs—i.e., it fetches and interprets untrusted third-party/user-generated content (public repos, server outputs, web/API responses) that can materially influence subsequent commands and decisions.