three-raycast-interaction
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide instructional code for 3D interactions. The logic is self-contained and operates within standard browser and WebGL boundaries.
- [COMMAND_EXECUTION]: There are no attempts to execute shell commands, perform privilege escalation, or access system-level resources.
- [DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive environment variables or local files (such as .ssh or .aws) were found.
- [EXTERNAL_DOWNLOADS]: The skill references the
threelibrary (version 0.169.0), which is a well-known and trusted package. No unverifiable or remote script executions are present. - [INDIRECT_PROMPT_INJECTION]: While the skill handles user pointer input, it does not process natural language instructions or interpolate untrusted data into agent prompts, presenting no injection risk.
Audit Metadata