newsman

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry, which is a required vendor resource for interacting with the Membrane platform.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to perform login, manage connections, and execute API actions on the Newsman service.
  • [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface for action discovery and creation. * Ingestion points: Natural language input for --intent and action DESCRIPTION parameters in SKILL.md. * Boundary markers: None present in the command templates. * Capability inventory: The CLI allows for network operations and remote execution of actions. * Sanitization: Relies on platform-level handling of input strings. This surface is necessary for the skill's primary natural language functionality.
  • [SAFE]: Implements secure credential management by leveraging the Membrane platform's authentication flow, ensuring no static API keys or secrets are exposed or stored in the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 07:38 PM
Security Audit — agent-trust-hub — newsman