peach-refactor-frontend
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to perform its core functions, including analyzing file structures and verifying code integrity. Specific commands include
ls,cat,bun run build,bun run lint:fix, andbunx vue-tsc. - [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
- Ingestion points: The skill reads source code from the local file system (e.g.,
front/src/modules/[모듈명]/**/*.{vue,ts}) to perform refactoring analysis. - Boundary markers: No explicit boundary markers or delimiters are used when reading files to distinguish between data (source code) and instructions.
- Capability inventory: The agent has permission to read/write to the file system and execute shell commands via the
bunruntime. - Sanitization: There is no evidence of sanitization or filtering of the processed source code to prevent embedded instructions from influencing agent behavior.
Audit Metadata