apollo-mcp-server

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download installation scripts and components from mcp.apollo.dev, which is an official resource provided by the vendor, Apollo GraphQL.
  • [REMOTE_CODE_EXECUTION]: Installation instructions include piping remote scripts from the vendor's domain directly to the system shell (sh for Linux/macOS, Invoke-Expression for Windows). These are documented as standard installation methods for the tool.
  • [COMMAND_EXECUTION]: Utilizes npx to execute MCP utilities including the remote connector (mcp-remote), the protocol inspector (@modelcontextprotocol/inspector), and a YAML validator (yaml-lint). It also references the rover CLI for GraphQL management.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with external GraphQL APIs, creating a surface for indirect prompt injection. Ingestion points: GraphQL API responses and schema definitions retrieved via uplink or local files. Boundary markers: None explicitly defined in the instructions. Capability inventory: File system access (Read/Write/Edit/Glob) and command execution via rover and npx. Sanitization: Not specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:52 PM
Security Audit — agent-trust-hub — apollo-mcp-server