The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches package metadata, review status, and check results from the official Comprehensive R Archive Network (CRAN) at cran.r-project.org. These requests target a well-known and authoritative service for the R programming language.
[COMMAND_EXECUTION]: Employs standard shell utilities including curl, grep, awk, and sed to interact with CRAN's directory structure and parse HTML responses. These operations are scoped to data retrieval and text processing.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface where user-provided inputs ({package} and {version}) are interpolated directly into shell command templates.
Ingestion points: User-supplied package and version strings processed in SKILL.md workflows.
Boundary markers: None; the shell templates do not use specific delimiters or instructions to isolate user input from the command structure.
Capability inventory: The skill utilizes curl, grep, awk, and sed for network interaction and parsing across multiple functions.
Sanitization: The workflow includes a step to strip a leading 'v' from version strings, but it lacks specific shell-escaping or validation for the package name placeholder to prevent command injection payloads.

r-cran-status