roblox-typescript-developer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data (source code and configuration files) and has access to command execution tools, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads project configuration (package.json, tsconfig.json, default.project.json) and source files (.ts files) to identify the project type and perform development tasks.
- Boundary markers: No explicit delimiters or warnings are used to separate user instructions from potentially malicious content within the processed files.
- Capability inventory: The skill environment allows for command execution (e.g., npm, npx, rojo) and file system modifications, which could be abused if an injection is successful.
- Sanitization: There are no instructions for sanitizing or validating the contents of external files before the agent acts upon them.
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools such as npm, npx, rojo, selene, and stylua. While these are legitimate tools for the intended workflow, they represent a capability that could be targeted by malicious instructions in project files.
Audit Metadata