game-analytics-setup
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to analyze game project files, telemetry definitions, and data logs using tools like
Read,Glob, andGrep. If the agent processes untrusted external data (e.g., logs or configuration files containing user-generated content), instructions embedded within that data could potentially influence the agent's behavior. - Ingestion points: The skill utilizes
Read,Glob, andGrepto access project-related files and data. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands when processing external files.
- Capability inventory: The skill allows high-capability tools including
Bash,Write, andEdit, which could be exploited if an indirect injection occurs. - Sanitization: No data validation or sanitization procedures are specified for handling external project content.
Audit Metadata