specialist-game-development-unity-unity-multiplayer-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates external data through the {the user's question} variable directly into a prompt for a sub-agent. This lacks structural boundaries to prevent the user input from potentially manipulating the sub-agent's instructions.
  • Ingestion points: User input is ingested via the {the user's question} placeholder in SKILL.md.
  • Boundary markers: The skill does not use XML tags, triple quotes, or other delimiters to isolate user input from the system instructions.
  • Capability inventory: The skill uses the Agent tool to spawn specialist sub-agents.
  • Sanitization: There is no evidence of input filtering, validation, or escaping for the user-provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-unity-unity-multiplayer-engineer