token-budget-advisor
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, focusing on internal reasoning to estimate token counts and adjust response length based on user selection.
- [SAFE]: There are no requests for file system access, network connectivity, or shell command execution.
- [SAFE]: The reference to an external GitHub repository is provided for informational purposes as the source of the technique and does not include instructions for the agent to download or execute remote scripts.
- [SAFE]: No prompt injection, obfuscation, or persistence mechanisms were detected.
Audit Metadata