manifest

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages the lifecycle of the Claude gateway using claude gateway stop and claude gateway install commands.- [EXTERNAL_DOWNLOADS]: The skill downloads and adds new capabilities to the environment by running claude plugins install manifest.- [COMMAND_EXECUTION]: The skill performs local configuration updates by interpolating user-provided API keys and endpoint URLs into the claude config set command.- [COMMAND_EXECUTION]: The skill reads from local log files (~/.claude/logs/gateway.log) using grep and tail to confirm the plugin is active.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — manifest