game-engagement-ideas
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation references a GitHub repository (
github.com/Playgama/gamedev-skills) for installation. These references point to the vendor's official resources and are documented neutrally. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external telemetry files and project metadata which could theoretically contain instructions designed to influence the agent's behavior.
- Ingestion points: The agent reads data from
analytics-data/README.md,analytics-data/manifest.json,AGENTS.md,CLAUDE.md, and telemetry data provided within the conversation. - Boundary markers: The instructions do not define explicit boundary markers or warnings to the agent to disregard instructions embedded in the analyzed data.
- Capability inventory: The skill is restricted to reading local project files (code and telemetry) and writing hypotheses to documentation files (e.g.,
docs/ideas.md). - Sanitization: No explicit sanitization or validation of the input data is specified in the skill's instructions.
Audit Metadata