tabletop-rpg-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference data for game design theory. It does not utilize any tools, perform network requests, or execute commands.
- [SAFE]: The included regex patterns in the validation files are used for static text analysis within the AI's conversational context and do not represent executable code or dynamic execution risks.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-supplied game designs for evaluation. 1. Ingestion points: User requests containing TTRPG mechanics for review (SKILL.md). 2. Boundary markers: The skill instructs the agent to ground responses in local reference files and correct the user based on that data. 3. Capability inventory: No tool usage, network operations, or file system modifications are enabled. 4. Sanitization: No explicit input sanitization is defined. Due to the lack of any actionable capabilities, this attack surface poses no significant risk.
Audit Metadata