gsd-project-researcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Step 3 ("Conduct Research") explicitly instructs the agent to use "Context7 MCP or WebSearch" to search public web content (e.g., "[domain] 2025 stack", competitor docs) and verify versions, meaning it programmatically fetches and interprets untrusted third‑party web pages as part of its mandatory workflow, which can materially influence recommendations and actions.