run-codex-exec

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

• Third-party content exposure detected (high risk: 0.70). The skill's prompt guidance (references/mission-gravity.md and references/prompt-template.md inside SKILL.md) explicitly tells dispatched Codex agents they may consult external public docs (e.g., "look at the npm page or the github examples directory"), which means agents are expected to fetch and interpret untrusted third-party web content that could materially influence their actions.