balance-check

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests and processes content from external game data files and design documents to generate reports and suggest modifications.
  • Ingestion points: Data files in assets/data/, formulas in design/balance/, design documents in design/gdd/, and a global lenses file at ../../docs/game-design-lenses.md (SKILL.md, Phases 2, 3, 4).
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the model to ignore potential instructions embedded within the game data.
  • Capability inventory: The skill uses Read, Glob, Grep, and Write tools, enabling it to read design data and write modifications to project files (Phase 6).
  • Sanitization: There is no evidence of content sanitization, escaping, or schema validation for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:18 PM
Security Audit — agent-trust-hub — balance-check