migration-planning

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts and tools provided in the nextjs-migration-toolkit repository. Specifically, it runs a setup script (scripts/setup.sh) and an AST analysis tool (src/bin/ast-tool.ts) using npx tsx to process project directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted source code and configuration files to generate its output.
  • Ingestion points: Reads contents from the user-provided pagesDir, srcDir, and packageJsonPath via the ast-tool.ts utility.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the data ingested from the source code.
  • Capability inventory: The skill can execute shell commands (bash, npx tsx) and write files to the local disk (.migration/plan.md).
  • Sanitization: There is no explicit sanitization or validation mentioned for the content extracted from the AST analysis before it is used to formulate the migration plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 01:58 PM