skill-creator

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and research content from the open web (Step 2: "Research on The Internet" — use /docs-seeker, WebFetch, Explore subagents) and to load plugin/marketplace sources from public GitHub/GitLab/URL marketplaces, meaning the agent will read and interpret untrusted public third‑party content as part of its workflow.