game-engine-resources
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches repository descriptions and code archives from the author's GitHub repository at
raw.githubusercontent.com/gmh5225/awesome-game-security. This is used to provide implementation details for specific tools. - [PROMPT_INJECTION]: The skill's architecture relies on ingesting third-party data from external repositories, which presents a surface for indirect prompt injection. 1. Ingestion points: Data is fetched from GitHub archive and description endpoints defined in
SKILL.md. 2. Boundary markers: Absent. The instructions do not define delimiters for the external content. 3. Capability inventory: The skill is limited to information retrieval and does not manifest dangerous capabilities such as file system writes or code execution inSKILL.md. 4. Sanitization: Absent. Data is processed directly from the source URLs. - [SAFE]: No other security issues were detected; the skill primarily provides technical documentation and informational resources without requesting high-privilege tool access.
Audit Metadata