Skills
skills/hktitan/cursor-sdk/cursor-hooks/Gen Agent Trust Hub

cursor-hooks

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: Documentation describes a feature where arbitrary shell commands are executed from a workspace configuration file during the agent lifecycle loop.
  • Evidence: references/file-format.md details the JSON structure of .cursor/hooks.json, specifying that the agent will execute strings provided in the command fields of preRun and postRun hooks.
  • [NO_CODE]: The skill package is composed entirely of markdown documentation files and contains no executable scripts, binaries, or source code files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 08:28 AM