The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exposes a potential surface for indirect prompt injection by reading application output into the agent context.
Ingestion points: The get_logs and get_errors tools, documented in references/nextjs-mcp-server.md, allow the agent to ingest application logs and runtime error messages.
Boundary markers: The skill does not provide explicit instructions or markers to help the agent distinguish between its own instructions and untrusted content that might be present in application logs.
Capability inventory: The agent has the ability to write to the file system using the scripts/page-generator.ps1 script and execute shell commands as part of the development workflow.
Sanitization: No sanitization or filtering of log data is mentioned before the data is processed by the agent.
[COMMAND_EXECUTION]: The skill includes a PowerShell utility (scripts/page-generator.ps1) used to automate the creation of directories and source files. It uses standard file system commands like New-Item and Set-Content.
[EXTERNAL_DOWNLOADS]: The skill integrates with next-devtools-mcp, a utility from a well-known service provider in the web development ecosystem, and uses standard package managers for dependency installation.

nextjs-development