gsd-phase-researcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 5 ("Research Domain Knowledge") explicitly instructs the agent to use "Context7 MCP or WebSearch" and to check official documentation, recent blog posts and articles—i.e., ingesting open/public web and user-generated content—which the agent will read and use to influence recommendations and next actions, creating an opportunity for indirect prompt injection.