game-designer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user game concepts, competitor analysis, and existing prototypes to generate design documents.\n
- Ingestion points: User descriptions, competitor research, and prototype inspections (SKILL.md Phase 1, LITE.md SOLVE Step 2).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.\n
- Capability inventory: The skill primarily generates text-based design artifacts (GDDs, spreadsheets, specs) and does not utilize file-system write or code execution tools within its instructions.\n
- Sanitization: No sanitization or filtering of external content is defined.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the dynamic command syntax in SKILL.md to execute shell commands at load time for context gathering.\n
- Evidence:
!cat skills/_shared/protocols/design-mindset-and-rules.md 2>/dev/null || trueand!cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".\n - Analysis: These commands are used to read local protocol and configuration files. They are benign and do not involve network exfiltration or sensitive system access.
Audit Metadata