blast-radius
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the agent to analyze Roblox source code and diffs. No evidence of malicious behavior, obfuscation, or data exfiltration was found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (code diffs and project files). While this presents an attack surface where a malicious diff could contain instructions aimed at the agent, the skill instructions include specific constraints to report only concrete risks and trace logical flows, which aligns with safe operating practices. The capability is limited to analysis within the agent's provided environment.
Audit Metadata