roblox-studio-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to interact with and modify Roblox Studio projects, which involves reading untrusted content such as script source code, game tree hierarchies, and instance properties. This creates an attack surface where malicious instructions could be embedded in a project to influence the agent's actions.
- Ingestion points: Data enters the agent's context through tools like
script_read,inspect_instance, andsearch_game_treeused to explore the Roblox project (SKILL.md). - Boundary markers: The skill lacks instructions for the agent to use delimiters or ignore instructions found within the project data it processes.
- Capability inventory: The skill possesses powerful capabilities including
multi_editfor writing scripts andexecute_luaufor code execution within the Roblox engine environment (SKILL.md). - Sanitization: There is no mention of sanitizing or validating external project data before it is interpreted or used to perform modifications.
Audit Metadata