specialist-game-development-roblox-studio-roblox-avatar-creator

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and metadata are consistent with its stated purpose of assisting in Roblox avatar creation. No malicious command execution, privilege escalation, or persistence mechanisms were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses a template that interpolates user input into a subagent's instructions, which is a standard pattern for multi-agent systems.
  • Ingestion points: Untrusted user input enters the agent context via the {the user's question} variable in SKILL.md.
  • Boundary markers: The user input is placed at the end of the subagent prompt; however, explicit delimiters or 'ignore' warnings for the interpolated string are absent.
  • Capability inventory: The skill is restricted to spawning a subagent and providing instructional guidance; no file system writes or network operations are present in this skill.
  • Sanitization: No explicit sanitization or filtering of the user variable is performed before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-game-development-roblox-studio-roblox-avatar-creator