token-saver-cursor
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a locally provided Node.js script (
scripts/audit.mjs) to perform a read-only audit of agent configuration files. This script is used to identify oversized instruction files, redundant rules, and excessive MCP server configurations.\n- [DYNAMIC_EXECUTION]: The audit process involves running Node.js logic to traverse local directories and parse configuration files (JSON, YAML, TOML) to generate optimization suggestions. The script does not use external dependencies or network access.\n- [SAFE]: Analysis of the instructions and the audit script confirms that the skill stays within its intended scope. While the script reads configuration files in the user's home directory (e.g.,~/.cursor/mcp.json), it does not access sensitive credential stores and lacks networking capabilities, preventing any data exfiltration.
Audit Metadata