wellgrow-setup
Warn
Audited by Snyk on Feb 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md requires registering and connecting to an external MCP server at https://wellgrow.ai/api/mcp and calling the MCP's onboarding/list_questions tools, so the agent will fetch and act on untrusted third-party content returned by that server.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and calling the external MCP endpoint https://wellgrow.ai/api/mcp at runtime, which returns questions/tool data that are injected into the agent's context and therefore directly control agent prompts/behavior.
Audit Metadata