anti-cheat-systems
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to fetch external content from the author's GitHub repository (
gmh5225/awesome-game-security). This includes the project's README, repository descriptions, and full code snapshots stored in text format. These resources are used to provide the agent with detailed technical context during research tasks. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) as it ingests untrusted data from external GitHub sources into the agent's context.
- Ingestion points: External data is fetched from URLs under
https://raw.githubusercontent.com/gmh5225/awesome-game-security/as specified in the 'Data Source' section ofSKILL.md. - Boundary markers: The skill does not provide specific delimiters or instructions to the agent to ignore potentially malicious commands embedded in the fetched external content.
- Capability inventory: While the skill itself does not define tools, the execution environment may provide the agent with capabilities such as shell access (
bash), file system operations, and network requests. - Sanitization: There are no explicit sanitization or validation steps for the content retrieved from the remote repository before it is processed by the agent.
Audit Metadata