roblox-debugging-bugfix
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the Roblox environment.
- Ingestion points: The agent processes data from get_console_output, script_read, and inspect_instance which can contain attacker-controlled strings.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the processed game data.
- Capability inventory: The skill utilizes multi_edit for file writes and execute_luau for code execution in the target environment.
- Sanitization: No sanitization or filtering logic is present to validate external content before processing.
Audit Metadata