skills/naimsolong/ai-software-agency/specialist-game-development-game-audio-engineer/Gen Agent Trust Hub
specialist-game-development-game-audio-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by interpolating user-provided text directly into a sub-agent prompt.
- Ingestion points: The variable
{the user's question}in theAgenttool call withinSKILL.mdis the primary entry point for untrusted data. - Boundary markers: The skill does not use delimiters, XML tags, or explicit "ignore embedded instructions" warnings around the user input placeholder.
- Capability inventory: The sub-agent instructions are limited to providing technical audio engineering advice; there are no definitions for file system modifications, network requests, or shell command execution that could be abused via injection.
- Sanitization: No sanitization, escaping, or schema validation is applied to the user input before it is passed to the sub-agent.
Audit Metadata