The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands (find, grep, wc) to scan and analyze project files. It also relies on an external CLI tool referred to as u (unity-cli) to list tests when available.
[PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from the user's project files, including C# source code, assembly definitions (.asmdef), and CI workflow configurations.
Ingestion points: Processes project-level files via grep and find commands, specifically reading assembly definitions, manifest.json, and .github/workflows or .gitlab-ci.yml files.
Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are provided when processing the output of these files into the final report.
Capability inventory: The skill utilizes shell commands and an external test runner CLI (u) to gather project data.
Sanitization: There is no evidence of sanitization or escaping of the content extracted from the project files before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references an external repository (github.com/nowsprinting/unity-coding-skills) for test design methodology. This is a neutral reference to documentation/guidelines and does not involve executing remote code.

review-testing