skills/naimsolong/ai-software-agency/specialist-game-development-unity-unity-shader-graph-artist/Gen Agent Trust Hub
specialist-game-development-unity-unity-shader-graph-artist
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the interpolation of untrusted user data into a sub-agent prompt.
- Ingestion points: The variable
{the user's question}inSKILL.mdis used to directly pass raw user input into the prompt for theAgenttool. - Boundary markers: There are no delimiters (e.g., XML tags or triple quotes) or negative constraints instructing the agent to ignore instructions embedded within the user's question.
- Capability inventory: The skill uses the
Agenttool to delegate tasks. While no direct file-system or network operations are present in this skill file, the sub-agent possesses capabilities inherent to its specialized role. - Sanitization: No filtering, escaping, or validation logic is applied to the user input before it is concatenated into the prompt string.
Audit Metadata