nextjs-migration-toolkit

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run npm install to set up dependencies and tsx to execute its internal analysis and transformation scripts (e.g., src/bin/ast-tool.ts). These are standard operations for a local development toolkit.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided source files for analysis, creating a potential surface for indirect prompt injection.
  • Ingestion points: Files and directories passed as arguments to ast-tool.ts, such as <pagesDir>, <srcDir>, and <file>.
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted code content from the agent's instructions.
  • Capability inventory: The tool performs file system operations including fs.readFileSync for input and fs.writeFileSync for logging progress and errors in a local .migration/ directory.
  • Sanitization: Input is parsed into an Abstract Syntax Tree using the ts-morph library, which interprets the data as code structure rather than natural language instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 01:59 PM