r-package-refactor
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing R scripts and project data to perform refactoring, which creates a surface for indirect prompt injection if the source files contain malicious instructions.
- Ingestion points: The skill analyzes project directory structures using
rtk lsand reads R scripts to extract functions and dependencies (SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within the R scripts being analyzed.
- Capability inventory: The skill instructions include executing the refactored code via
devtools::load_all(),shiny::runApp(), andsource("main.R"), and performing file operations withmkdirandcp(SKILL.md). - Sanitization: The instructions do not specify any sanitization or validation steps for the content of the scripts before they are loaded or executed in the development environment.
Audit Metadata