skills/naimsolong/ai-software-agency/specialist-game-development-blender-blender-addon-engineer/Gen Agent Trust Hub
specialist-game-development-blender-blender-addon-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates the user's input variable directly into a subagent prompt, which could allow a malicious user to influence or override the subagent's intended behavior through the input data.
- Ingestion points: The
{the user's question}variable within theAgenttool call inSKILL.mdaccepts untrusted data. - Boundary markers: None (the variable is not wrapped in delimiters or accompanied by instructions to ignore embedded commands).
- Capability inventory: The skill utilizes the
Agenttool to spawn subagents, which potentially grants the subagent access to other platform capabilities. - Sanitization: No input sanitization or validation is applied to the user input before it is used in the prompt template.
Audit Metadata