game-multiplayer
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from
.gameforge/project.jsonand thedesign/folder to tailor its architectural advice. While this introduces an input surface for untrusted data, the skill is configured to output static documentation (ADRs and test plans) and explicitly instructs the agent to enforce server-side validation, significantly limiting the impact of potential injection attacks. - [COMMAND_EXECUTION]: Documentation within
references/testing-and-cost.mdincludes shell commands for thetcutility (e.g.,sudo tc qdisc) to simulate network conditions. These are presented as educational references for developers to perform manual network testing and are not intended for automated execution by the AI agent.
Audit Metadata