Manifest

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard installation and configuration tasks for an observability service using the platform's native command-line interface.
  • [COMMAND_EXECUTION]: Uses local CLI commands (claude gateway stop, claude plugins install, claude config set) to manage the agent's environment. These operations are consistent with the skill's stated purpose of plugin management.
  • [EXTERNAL_DOWNLOADS]: Downloads the 'manifest' plugin via the official claude plugins install command, which is the designated extension mechanism for the agent platform.
  • [CREDENTIALS_SAFE]: Instructs the agent to prompt the user for an API key starting with the legitimate mnfst_ prefix and configures it locally without leaking it to external logs or services.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 12:56 PM
Security Audit — agent-trust-hub — Manifest