r-package-check
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute various shell commands including Rscript, git, and R CMD check for package verification and drift detection.
- [DYNAMIC_EXECUTION]: R command strings are dynamically constructed by interpolating the package path variable directly into R code snippets passed to Rscript -e. This pattern lacks sanitization, meaning a maliciously crafted directory name could potentially escape the string literal and execute arbitrary R code.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes R package contents and check outputs to determine if a package is CRAN-ready, creating a surface for indirect prompt injection.
- Ingestion points: The package root directory and its contents, including the DESCRIPTION file, NAMESPACE, and source code files.
- Boundary markers: Absent; the skill instructions do not define specific delimiters or instructions for the agent to ignore content within the package files.
- Capability inventory: The skill has access to the Bash, Task, and Monitor tools, enabling the execution and monitoring of shell commands.
- Sanitization: Absent; the skill does not implement validation or escaping of the package data before it is processed for the release gate report.
Audit Metadata