r-tidyverse-style
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for the agent to review and clean up R code. It includes specific safety guidelines to preserve public behavior, protect exported interfaces, and prioritize established package conventions over style rules.
- [EXTERNAL_DOWNLOADS]: The skill references the official Tidyverse style guide and its associated GitHub repository. These are well-established and trusted resources in the R programming community.
- [COMMAND_EXECUTION]: The skill mentions optional CLI tools (
air,jarl,ry) for formatting and linting. The instructions require honoring existing project configurations and investigating diagnostics rather than automatic application, following developer best practices. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes R source files, tests, and package metadata. While it lacks explicit boundary markers or sanitization, the instructions are focused on behavior-preserving cleanup and cautious refactoring. Evidence chain: 1. Ingestion points: R source files, tests, and DESCRIPTION file. 2. Boundary markers: Absent. 3. Capability inventory: File reading, modification, and execution of R formatting tools. 4. Sanitization: Absent.
Audit Metadata