game-design
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to autonomously ingest and act upon untrusted content from game repositories.
- Ingestion points: As described in
SKILL.md(Section 1: Intake) andreferences/autonomous-improvement.md, the skill reads variety of files including design documents, player-facing copy, combat logs, and issue reports from the target repository. - Boundary markers: Absent. There are no instructions to wrap ingested data in delimiters or to ignore embedded instructions within processed files.
- Capability inventory: The skill has access to a broad set of tools including
Bash,Write,Edit, andRead, as defined in theSKILL.mdfrontmatter. - Sanitization: Absent. The skill does not define any filtering, escaping, or validation logic for the external repository content before it is processed by the AI agent.
Audit Metadata