using-next-devtools

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes tools such as upgrade_nextjs_16 and nextjs_auto_fix to perform automated modifications to the project's source code and configuration. These actions involve executing codemods and package management commands (e.g., npm or yarn) to update dependencies and apply fixes.
  • [PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection (Category 8) due to its interaction with untrusted local data.
  • Ingestion points: The agent reads project-level metadata from package.json, analyzes local source code files for optimization, and retrieves runtime error logs or routing information from a local development server.
  • Capability inventory: The skill has extensive write capabilities, including the ability to insert "use cache" directives, set Suspense boundaries, and apply automated code fixes to the codebase.
  • Boundary markers: There are no defined delimiters or specific instructions provided to the agent to treat data from the project files as untrusted or to ignore embedded instructions within those files.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the data ingested from the project environment before it influences the agent's code modification logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 02:12 PM