run-r-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes R scripts and parameter lists provided via user-defined paths, which represents a surface for indirect instructions. Ingestion points: File paths and parameters (
script_path,params) as defined in SKILL.md. Boundary markers: Absent; the instructions do not specify the use of delimiters or ignore-instructions for the processed files. Capability inventory: High-privilege code execution viasource(),rmarkdown::render(), andquarto::quarto_render()as described in SKILL.md. Sanitization: Absent; no content validation or sanitization is performed on the scripts before execution. - [DYNAMIC_EXECUTION]: The skill facilitates the runtime execution of R code using
source()andquarto::quarto_render()on files targeted by the user. This functionality is the primary intended purpose of the skill and relies on standard R execution methods within a project context.
Audit Metadata