specialist-game-development-roblox-studio-roblox-systems-scripter

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through the direct interpolation of untrusted data into sub-agent prompts.
  • [PROMPT_INJECTION]: Ingestion point: User data is ingested via the '{the user's question}' placeholder in the SKILL.md file.
  • [PROMPT_INJECTION]: Boundary markers: The prompt lacks delimiters (such as XML tags or triple quotes) to separate user input from the system instructions.
  • [PROMPT_INJECTION]: Capability inventory: The skill possesses the capability to spawn new specialist agents with specific instructions using the Agent tool.
  • [PROMPT_INJECTION]: Sanitization: There is no evidence of validation, escaping, or filtering of the interpolated user content.
  • [NO_CODE]: The skill consists of markdown instructions only and does not contain executable scripts or reference external packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-roblox-studio-roblox-systems-scripter