roblox-game-balance
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing external project data, such as configuration files, design rules, and persistence schemas. This creates an attack surface where malicious instructions embedded in these data sources could potentially influence the agent's behavior.
- Ingestion points: As specified in
SKILL.md, the agent is instructed to readAGENTS.md, design rules, server configuration, persistence schema, monetization configuration, and analytics definitions. - Boundary markers: The skill mitigates risks by requiring the agent to "Inspect current values at their actual source of truth" rather than relying on potentially deceptive UI elements or screenshots.
- Capability inventory: The agent can propose configuration changes and define telemetry/metrics for the system being analyzed.
- Sanitization: The instructions include a mandatory validation step for all client-supplied quantities, target IDs, and ownership at the implementation boundary.
Audit Metadata