specialist-game-development-narrative-designer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a sub-agent orchestration pattern that interpolates raw user input into a sub-agent's prompt without using boundary markers or sanitization.
  • Ingestion point: User input is passed as {the user's question} within the prompt string in SKILL.md.
  • Boundary markers: Absent. The input is not delimited to prevent it from escaping the intended context.
  • Capability inventory: The skill utilizes the Agent tool to delegate tasks to specialist sub-agents.
  • Sanitization: Absent. There is no evidence of filtering or escaping logic applied to the user-supplied content before it is processed by the sub-agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-narrative-designer