gsp-mechanics-systems-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve ingesting untrusted external data (game concepts) to generate design documents and persistent files. This creates a surface for indirect prompt injection where malicious instructions within a game concept could influence the agent's behavior.
- Ingestion points: User-provided game concepts are processed to create system designs in
SKILL.md. - Boundary markers: Absent; the skill does not specify delimiters or warnings to ignore instructions embedded in the design concepts.
- Capability inventory: The skill instructs the agent to write files to the local file system (e.g.,
docs/game-studio/system-design.mdandchanges/<change-id>/design.md). - Sanitization: Absent; no validation or filtering of the input concept data is specified.
Audit Metadata