MCP Integration

Fail

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill configures access to external data sources and local files, creating a high-risk injection surface.
  • Ingestion points: External content from GitHub (mcp.github.com), Asana (mcp.asana.com), and local files (${CLAUDE_PROJECT_DIR}).
  • Boundary markers: None present; the configuration does not define delimiters or instructions to ignore embedded commands in fetched data.
  • Capability inventory: File system read/write via @modelcontextprotocol/server-filesystem, database access via db-server.js, and execution of custom Python tools.
  • Sanitization: No sanitization or validation logic is defined in these configuration files.
  • [Remote Code Execution] (HIGH): The stdio-server.json file utilizes npx -y to execute a package.
  • Evidence: npx -y @modelcontextprotocol/server-filesystem in examples/stdio-server.json downloads and executes code from the npm registry at runtime. Since @modelcontextprotocol is not in the trusted source list, this is a high-risk operation that bypasses static code review.
  • [Command Execution] (MEDIUM): Multiple sections define arbitrary command execution.
  • Evidence: Execution of ${CLAUDE_PLUGIN_ROOT}/servers/db-server.js and python -m my_mcp_server allows the agent to run local processes with environment-variable-injected credentials.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:54 PM