add-rcpp-integration
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The procedure includes creating a cleanup shell script and using 'chmod +x' to make it executable, which is a common requirement for R packages but involves creating executable files at runtime (SKILL.md).
- [COMMAND_EXECUTION]: The skill utilizes R development tools like 'Rcpp::compileAttributes()' and 'devtools::load_all()' to compile C++ source code into shared libraries and load them into the R environment, representing runtime code generation and execution (SKILL.md).
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to process and modify existing R packages and functions provided by the user.
- Ingestion points: User-provided R package directory and R function definitions (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Directory creation, file modification (Edit/Write), shell command execution (Bash), and runtime code compilation/loading (SKILL.md).
- Sanitization: Absent.
Audit Metadata