update-claude-code

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download of the '@anthropic-ai/claude-code' package from the npm registry. This is an official package from a trusted organization.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands, including 'npm install -g' for software installation and 'rm -rf' for deleting specific version-related directories in the user's local share folder. These operations are constrained to managing the specified tool.
  • [REMOTE_CODE_EXECUTION]: The skill contains a reference to a 'curl | bash' installation method for the Claude CLI; however, it explicitly warns against using this method and favors the npm-based approach for reliability.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 09:01 AM