busirocket-refactor-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions mandate the execution of local project scripts, specifically
yarn check:all,yarn type-check,yarn format, andyarn lint. These commands are standard for verifying code integrity in TypeScript environments and are intended to be run within the user's controlled project workspace. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and refactor user-provided source code files, creating a vulnerability surface for indirect instructions.
- Ingestion points: TypeScript (
.ts,.tsx) files targeted for refactoring referenced via the@fileconvention. - Boundary markers: Absent; the skill lacks specific delimiters to isolate user code from agent instructions.
- Capability inventory: Subprocess execution of
yarnscripts for linting and type-checking. - Sanitization: Absent; the workflow relies on the effectiveness of external compilers and linters to catch errors rather than sanitizing inputs.
Audit Metadata