The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze arbitrary Ruby source code and git diffs, creating an attack surface for indirect prompt injection.
Ingestion points: Reads file contents via git ls-files and rg (ripgrep) to identify anti-patterns in local source code.
Boundary markers: No explicit delimiter or sanitization instructions are provided to the agent for the processed code snippets.
Capability inventory: The skill uses git for repository inspection and rg for text searching; it also has the ability to load additional skills.
Sanitization: No specific sanitization or escaping of the ingested code is implemented before interpolation into the analysis report.
[EXTERNAL_DOWNLOADS]: The skill references a dependency hosted in the author's GitHub repository.
Evidence: Instructions include a fallback command: npx skills@latest add bostonaholic/skills --skill simplifying-ruby-code.
Context: This command fetches a modular sub-skill provided by the same author to extend the analysis capabilities. This is consistent with the platform's intended modularity and the author's own infrastructure.
[COMMAND_EXECUTION]: The skill utilizes shell commands for repository and file analysis.
Commands: git ls-files, git diff, and rg -n are used to determine the scope of the audit and identify code patterns. These are standard, low-privilege operations expected for a code analysis tool.

reviewing-ruby-code