balance-check
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and summarizes content from game data and design documents which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads files from assets/data/, design/balance/, design/gdd/, and user-provided paths via the path-to-data-file argument.
- Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between data content and instructions.
- Capability inventory: The skill uses Read, Glob, and Grep tools; it does not possess high-risk capabilities such as network access, file-writing, or shell command execution.
- Sanitization: No input validation or content filtering is performed on the data ingested from the files.
Audit Metadata