omniconvert

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official @membranehq/cli package from the NPM registry to enable integration capabilities.
  • [COMMAND_EXECUTION]: Uses the membrane CLI tool to perform authorized operations such as listing actions, running experiments, and proxying requests to the Omniconvert API.
  • [PROMPT_INJECTION]: As an integration skill, it processes data from external sources (Omniconvert API) which represents a surface for indirect prompt injection.
  • Ingestion points: API responses from membrane action run and membrane request are processed by the agent.
  • Boundary markers: The instructions do not define specific delimiters for separating external data from system instructions.
  • Capability inventory: The skill allows the agent to execute shell commands (via the Membrane CLI) and make network requests (via the proxy).
  • Sanitization: Data is processed as-is from the API responses without explicit sanitization steps described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 08:33 AM