skills/naimsolong/ai-software-agency/specialist-game-development-godot-godot-multiplayer-engineer/Gen Agent Trust Hub
specialist-game-development-godot-godot-multiplayer-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by interpolating user-controlled data into the system instructions of a generated subagent.
- Ingestion points: The variable
{the user's question}in theAgenttool call withinSKILL.md. - Boundary markers: Absent. The user input is placed directly at the end of the prompt without delimiters or instructions to treat it strictly as data.
- Capability inventory: The skill uses the
Agenttool to delegate tasks to subagents. - Sanitization: No sanitization, escaping, or validation is performed on the user input prior to its inclusion in the subagent's prompt.
Audit Metadata