The Agent Skills Directory

[SAFE]: The skill performs project analysis using standard shell commands (ls, find, grep, mkdir) to detect technology stacks and directory structures. This is consistent with its stated purpose of project initialization.
[SAFE]: No network operations, external downloads, or remote code execution patterns were identified. The skill operates entirely on the local file system.
[SAFE]: The skill generates configuration that includes security best practices, such as explicitly denying read access to sensitive environment and secret files in the generated .claude/settings.json template.
[SAFE]: No evidence of prompt injection, obfuscation, or data exfiltration was found in the instructions or the workflow steps.

init-claude