mastergo

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime scripts (notably scripts/mastergo_get_dsl.py which fetches DSL JSON from mastergo.com and resolves short links, and scripts/mastergo_fetch_docs.py which fetches component documentation from URLs extracted from the DSL) retrieve and feed arbitrary public third-party content (MasterGo files and linked documentation pages) into the agent's analysis workflow, exposing it to untrusted user-generated content that could carry indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill clearly fetches arbitrary component documentation URLs at runtime (see mastergo_fetch_docs.py which fetches links like "https://example.com/button.mdx" extracted from componentDocumentLinks) and outputs that remote content into the agent workflow, meaning externally-hosted documents can be injected into the model context and directly influence prompts and generated code.