pg-status

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and displays marketplace/user-provided content (e.g., "proxygate apis", "proxygate listings docs ", and "proxygate jobs get ") as shown in SKILL.md and references/commands.md, meaning the agent would read untrusted third-party listing/docs/job text that could influence its subsequent actions.