specialist-game-development-unity-unity-architect

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user input directly into a sub-agent's system prompt without boundary markers.
  • Ingestion points: The variable {the user's question} in SKILL.md captures arbitrary user input.
  • Boundary markers: The skill lacks delimiters (e.g., triple quotes, XML tags) to separate user content from the architect's instructions.
  • Capability inventory: The skill uses the Agent tool to spawn specialist sub-agents, which could be misdirected by a malicious input payload.
  • Sanitization: There is no evidence of filtering or escaping for the interpolated user content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-unity-unity-architect