The Agent Skills Directory

[Command Execution for Code Analysis]: The skill utilizes the grep utility to scan provided source files for specific performance-related patterns, such as async void or inefficient string concatenations. These are read-only operations used for identifying optimization opportunities.
Evidence: Pattern detection recipes are included in SKILL.md and reference files like references/async-patterns.md and references/collections-and-linq.md.
[Processing of External Source Code]: The skill is designed to ingest and analyze user-provided codebases. This creates a surface for indirect prompt injection if the analyzed files contain instructions designed to influence the agent's output. This is a common characteristic of static analysis tools.
Ingestion points: The skill defines "Source code" as a primary input in SKILL.md.
Boundary markers: No explicit markers are defined to separate code from instructions.
Capability inventory: The skill uses grep for file scanning.
Sanitization: No explicit sanitization or filtering of the input source code is described.

analyzing-dotnet-performance