context-budget-audit
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely instructional and does not include any scripts, executable tools, or automated tasks. It provides a manual framework and pseudocode for an agent to follow.
- [SAFE]: While the audit process involves reading local configuration files like
~/.claude.jsonandsettings.jsonto estimate token overhead, these actions are restricted to the local environment and are necessary for the skill's stated purpose. No network operations or data exfiltration patterns were detected.
Audit Metadata