The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized behaviors were detected. The skill's instructions focus on providing architectural advice for backend testing strategies.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to ingest and analyze existing codebase content. This is an inherent risk factor for skills that interact with external project data.
Ingestion points: Analyzes project files using the Read, Grep, and Glob tools in the local environment.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the analyzed code comments or data files.
Capability inventory: The skill is configured with access to Bash, Write, and Edit tools, allowing it to modify files or execute commands based on its analysis.
Sanitization: No content sanitization or filtering logic is specified for data retrieved from the codebase.
[EXTERNAL_DOWNLOADS]: The skill provides references to official documentation and educational resources from well-known services and trusted sources, including Martin Fowler, Pytest, Testcontainers, Pact, and GitHub.

backend-testing