The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to analyze untrusted content from the user's project. * Ingestion points: The agent is instructed in SKILL.md to read project configuration and source files such as spec/spec_helper.rb, Gemfile, and various application logic files. * Boundary markers: The skill does not employ delimiters or instructions to ignore potential commands within the processed external files. * Capability inventory: The skill possesses the capability to read local files and generates shell commands for user execution based on the analyzed data. * Sanitization: There is no validation, escaping, or filtering of the ingested file content before it is processed.
[EXTERNAL_DOWNLOADS]: The skill references an external dependency from a well-known service. references/bottlenecks.md suggests fetching the simplecov gem directly from the official simplecov-ruby organization on GitHub to utilize performance-oriented coverage modes.

testprof