skills/naimsolong/ai-software-agency/specialist-game-development-unity-unity-multiplayer-engineer/Gen Agent Trust Hub
specialist-game-development-unity-unity-multiplayer-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates external data through the
{the user's question}variable directly into a prompt for a sub-agent. This lacks structural boundaries to prevent the user input from potentially manipulating the sub-agent's instructions. - Ingestion points: User input is ingested via the
{the user's question}placeholder inSKILL.md. - Boundary markers: The skill does not use XML tags, triple quotes, or other delimiters to isolate user input from the system instructions.
- Capability inventory: The skill uses the
Agenttool to spawn specialist sub-agents. - Sanitization: There is no evidence of input filtering, validation, or escaping for the user-provided content.
Audit Metadata