shift
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase files and possesses capabilities that could be exploited via indirect prompt injection.
- Ingestion points: The skill reads source code and configuration files (e.g., package.json, tsconfig.json) from the user's project during the ASSESS and PREPARE phases.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded prompts when processing file content.
- Capability inventory: The skill can execute jscodeshift (dynamic code execution), run npx commands, and perform package manager operations across all files.
- Sanitization: No sanitization or escaping of external content is performed before analysis or interpolation.
- [DYNAMIC_EXECUTION]: The skill generates and executes AST-based transformation scripts (codemods) at runtime to automate codebase migrations across various languages.
- [EXTERNAL_DOWNLOADS]: The skill automates the execution of migration tools and codemods from remote repositories, including official framework migrators (e.g., react-codemod, vue-codemod, @next/codemod) and OpenRewrite recipes.
- [COMMAND_EXECUTION]: The skill utilizes shell commands to perform audits, execute migrations, and manage dependencies (e.g., npm audit, npx jscodeshift, mvnw rewrite:run).
Audit Metadata