whatcounts

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to install and use the membrane command-line utility for managing service connections and executing API actions.
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to download and install the @membranehq/cli package from the official NPM registry.
  • [PROMPT_INJECTION]: As the skill retrieves and processes data from an external service (WhatCounts), it possesses a surface for indirect prompt injection from untrusted data in email campaigns or subscriber records.
  • Ingestion points: API responses fetched through the membrane action run and membrane request commands.
  • Boundary markers: The skill does not explicitly define delimiters for external data within the prompt instructions.
  • Capability inventory: The skill can execute shell commands via the CLI and perform network operations.
  • Sanitization: Data sanitization and validation are delegated to the underlying Membrane platform and CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:53 PM
Security Audit — agent-trust-hub — whatcounts