specialist-game-development-godot-godot-gameplay-scripter

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill interpolates user-controlled data directly into a sub-agent's system prompt without providing boundary markers or instructions to ignore embedded commands within the input.
  • Ingestion points: The user's question is interpolated into the Agent tool call in SKILL.md via the {the user's question} placeholder.
  • Boundary markers: There are no delimiters (like XML tags or triple quotes) used to separate the instructions from the user input, nor are there instructions telling the agent to treat the input as data only.
  • Capability inventory: The skill uses the Agent tool to spawn sub-specialists, which inherits the agent's broad capabilities.
  • Sanitization: No escaping, filtering, or validation is performed on the user's input before it is concatenated into the prompt string.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-godot-godot-gameplay-scripter