game-security-research-rigor

---
name: game-security-research-rigor
description: Verify consequential or disputed game-security claims with primary sources, reproducible evidence, explicit trust boundaries, and calibrated uncertainty. Use alongside a domain skill when evidence quality affects the conclusion.
---

# Game security research rigor

Keep conclusions no stronger than the evidence. Separate observation, finding, attribution, and action, and record temporal and environmental limits.

## Topic routing

- [Claims and workflow](references/claims-and-workflow.md) for reasoning layers, research steps, and versioned claim records.
- [Evaluation and governance](references/evaluation-and-governance.md) for detector metrics, invariants, decision policy, quality gates, and test limits.
- [Sources](references/sources.md) and [repository evidence](references/repository-evidence.md) for source roles and collection-specific evidence.
- [Robustness and triage](references/robustness-and-triage.md) for confounders, adversarial inputs, and disagreement.
- [Skill evaluation](references/skill-evaluation.md) for catalog routing tests.

State what would falsify the conclusion and what evidence remains unavailable. Do not convert a repository summary, community report, or absence of evidence into a verified product claim.

More agent context in gmh5225/awesome-game-security

14 other files this repository gives its agents.