brainstorm
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a standard creative facilitation workflow. It uses local file read/write operations to manage game design documents within a specific directory (
design/gdd/). - [DATA_EXPOSURE_EXFILTRATION]: While the skill uses
WebSearch, it is used for market research and engine recommendations relevant to the user's game concept. There is no evidence of sensitive data access or unauthorized exfiltration. - [COMMAND_EXECUTION]: The skill mentions various slash commands (e.g.,
/setup-engine,/prototype) as suggested next steps for the user. These appear to be pointers to other integrated tools or skills within the agent's environment rather than direct command execution strings. - [PROMPT_INJECTION]: No evidence of malicious prompt injection or instructions to bypass safety guidelines was found. The instructions are focused on the creative process.
- [INDIRECT_PROMPT_INJECTION]: The skill reads existing design files to resume work. While this is an ingestion point for external data, it is a standard feature for a documentation tool and poses no significant risk in this context.
Audit Metadata