game-design-review
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because its core function involves ingesting and analyzing untrusted content from the local project directory.
- Ingestion points: The skill reads Game Design Documents (markdown, text, PDF), configuration files (JSON, YAML, XML), and project source code to perform its evaluation.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed documents, which could allow external data to influence agent behavior.
- Capability inventory: The skill uses file reading capabilities for analysis and file writing capabilities to append telemetry logs to
~/.claude/projects/. - Sanitization: There is no explicit sanitization or validation of the data extracted from project files before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to write execution telemetry to
~/.claude/projects/to support the self-evolution of the tool. While this interaction occurs outside the project root, it targets the platform's standard project memory directory for local logging purposes.
Audit Metadata