gsp-production-feature
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional markdown that provides guidelines for feature development. It does not contain any executable scripts, shell commands, or network-enabled tools.
- [PROMPT_INJECTION]: The skill is designed to process user-provided game feature requests, which creates a theoretical surface for indirect prompt injection.
- Ingestion points: User-supplied game feature scope and requirements mentioned in SKILL.md.
- Boundary markers: Absent; there are no instructions to the agent to disregard commands embedded within the feature requests.
- Capability inventory: The skill directs the agent to implement feature code and write to documentation files like
docs/game-studio/quality-target.md. - Sanitization: Absent; no validation or input cleaning is specified for the user-provided content.
Audit Metadata