token-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions providing templates for reporting token usage and cost estimates.
- [NO_CODE]: There are no executable scripts (Python, JavaScript, Shell) or binaries included in the skill; it relies entirely on the agent's internal reasoning and formatting capabilities.
- [EXTERNAL_DOWNLOADS]: The skill provides a link to the official Anthropic console for usage monitoring and mentions standard Claude CLI configuration commands, both of which are trusted and well-known services.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user input and code to estimate token counts, it lacks the capabilities (such as network operations or file-writing tools) required to facilitate an exploit, making the surface area benign.
Audit Metadata