specialist-game-development-unreal-engine-unreal-world-builder

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection where user-supplied content is interpolated directly into a subagent's instructions.
  • Ingestion points: The {the user's question} variable in SKILL.md is directly embedded into the prompt argument of the Agent() tool call.
  • Boundary markers: No boundary markers, such as XML tags, triple backticks, or explicit instructions to ignore embedded commands, are present to isolate the user input from the system instructions.
  • Capability inventory: The skill leverages the Agent tool to spawn subagents, which involves passing instructions to another LLM instance.
  • Sanitization: There is no evidence of input validation, escaping, or filtering applied to the user input before it is used to construct the subagent prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-unreal-engine-unreal-world-builder