shift
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and executes transformation scripts (codemods) to automate code changes across the project. This is the primary function for library and framework migrations and follows best practices such as performing dry-runs before final execution.- [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run developer tools such as jscodeshift, which involves downloading these packages from the well-known npm registry. These downloads originate from a reputable and established service.- [PROMPT_INJECTION]: The skill processes codebases and database schemas, creating a surface for indirect prompt injection where instructions hidden in the codebase could theoretically influence agent behavior.\n
- Ingestion points: Project source code and database schemas are analyzed during the assessment and execution phases.\n
- Boundary markers: The skill does not explicitly specify delimiters or instructions to ignore embedded content when processing project files.\n
- Capability inventory: The skill is capable of shell command execution (via npx and database tools), filesystem modifications (writing codemods), and network operations for behavioral verification.\n
- Sanitization: There is no explicit mention of sanitizing or filtering project content before processing it for migration planning.
Audit Metadata