gsp-production-code
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its reliance on external data to influence agent behavior.\n
- Ingestion points: References to local project files
../../shared/checklists/production-code-checklist.mdand../../shared/reference/game-dev-abstractions.mdinSKILL.md.\n - Boundary markers: The skill does not define specific boundaries or instructions to ignore potential instructions within referenced files.\n
- Capability inventory: The skill is capable of modifying files, specifically
docs/game-studio/architecture.mdanddocs/game-studio/quality-target.md.\n - Sanitization: There is no evidence of sanitization or validation of the content read from the reference files before it is used to generate or update documentation.
Audit Metadata