gsp-rolling-supervisor
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to autonomously process and repair external project files, which creates a surface for instructions embedded in untrusted project data to influence agent behavior.
- Ingestion points: Project files, build logs, and verification results processed during the rolling supervisor passes (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its own logic and instructions that might be present in the project data.
- Capability inventory: The skill possesses the ability to write to project files (
docs/game-studio/...) and manage project state through 'verify/repair' cycles. - Sanitization: The instructions do not define any sanitization or validation steps for the content ingested from the external repository.
Audit Metadata