payabli-mcp-setup
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow installs/uses an MCP server that answers questions by searching and returning Payabli documentation content (public web/docs text) into the agent’s LLM context via the MCP tool calls, which is outsider-authored free text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to install and use the external MCP endpoint at https://mcp.inkeep.com/payabli/mcp during runtime so the agent will call that service for Q&A (its responses directly influence agent prompts/behavior), which makes it a runtime external dependency that can control prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata