roblox-quest-progression-systems
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.
- Ingestion points: The agent is instructed to search for and read external quest, progression, and UI scripts from the development environment (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or directives to treat the ingested code as untrusted data, which could allow instructions hidden in comments within the code to influence agent behavior.
- Capability inventory: The workflow includes the use of
multi_editandexecute_luau, providing the agent with the ability to modify and run code based on the potentially untrusted input (SKILL.md). - Sanitization: There are no instructions to sanitize or validate the content of the read scripts before processing or execution.
Audit Metadata