context-budget

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs read-only operations on standard configuration files within the agent's project environment (such as agents/, skills/, rules/, .mcp.json, and CLAUDE.md) for the purpose of token estimation and optimization.
  • [SAFE]: No network operations, external downloads, or data exfiltration patterns were detected. All analysis is performed locally on project metadata and file statistics using word and line counts.
  • [SAFE]: The skill does not execute arbitrary code or shell commands. Its logic is restricted to parsing text files that the agent already has access to in its project scope.
  • [SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were found in the skill's instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:19 AM
Security Audit — agent-trust-hub — context-budget