skills/justinedevs/roblox-ai-os/help/Gen Agent Trust Hub

help

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a domain-specific language for Roblox creation that processes untrusted user input, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in command arguments.\n
  • Ingestion points: User-provided arguments for commands including $brief, $blueprint, and $forge (SKILL.md).\n
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these inputs.\n
  • Capability inventory: The skill has access to shell inspection (rcs sparkshell) and process management (rcs team) (SKILL.md).\n
  • Sanitization: No evidence of input validation or sanitization logic is provided in the skill documentation.\n- [COMMAND_EXECUTION]: The skill documentation explicitly guides the agent to perform system-level operations using a local command-line interface.\n
  • Evidence: References to rcs setup (installs components), rcs doctor (health checks), and rcs sparkshell (shell inspection) in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 11:36 AM
Security Audit — agent-trust-hub — help