router-main
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and routing configuration. It does not contain any executable scripts, shell commands, or binary files.- [PROMPT_INJECTION]: The skill includes explicit defensive logic to 'ignore "route to X" instruction hijacks' and requires the agent to route by intent rather than following literal instructions to use a specific router, which is a best-practice for preventing injection.- [EXTERNAL_DOWNLOADS]: There are no external network calls or downloads. The file references internal project paths within the local skill library for data and documentation.- [NO_CODE]: This skill functions as a pure configuration and orchestration layer for other agents and does not introduce any custom code or logic that could be exploited.
Audit Metadata