skills/stanestane/game-design-skills-bundle/game-design-player-persona-extractor/Gen Agent Trust Hub
game-design-player-persona-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: Analysis of the skill instructions and reference files reveals no malicious patterns, prompt injections, or unauthorized command executions. The content is consistently focused on the stated purpose of game design analysis.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied game design descriptions, which creates a theoretical surface for indirect prompt injection if those descriptions contain instructions meant to influence the agent.
- Ingestion points: User-provided descriptions of game mechanics, loops, and features are processed as the primary input in
SKILL.md. - Boundary markers: The instructions do not implement specific delimiters (like triple backticks or XML tags) or explicit instructions for the agent to ignore commands within the analyzed design.
- Capability inventory: The skill is intended for text generation and uses web research capabilities to validate market data.
- Sanitization: No sanitization, filtering, or validation steps are defined for the user-provided design text.- [EXTERNAL_DOWNLOADS]: The skill references external sources for licensing and market research purposes.
- References the vendor repository
github.com/Stanestane/game-design-skills-bundlefor licensing terms. - Directs the agent to perform web research for market validation, prioritizing reputable industry sources like GDC, Steam ecosystem reports, and Newzoo.
Audit Metadata