The Agent Skills Directory

[SAFE] (SAFE): No malicious code, obfuscation, or unsafe command executions were detected in the skill instructions.
[Indirect Prompt Injection] (LOW): The skill is designed to read project files, documentation, and commit history. This creates a surface where untrusted data (from project files) enters the agent's context. However, the skill does not grant elevated privileges or perform sensitive network operations based on this data, and the risk is inherent to the tool's primary purpose of analyzing project context.

brainstorming