Skills
skills/membranedev/application-skills/kontomatik/Gen Agent Trust Hub

kontomatik

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 Membrane CLI (@membranehq/cli) from the official npm registry. This is a vendor-provided tool required for the skill's functionality.
  • [COMMAND_EXECUTION]: Executed shell commands (e.g., membrane login, membrane action run) are used to interact with the Membrane platform and manage Kontomatik data. These commands are standard for this integration.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external financial data and user-defined intents.
  • Ingestion points: Data returned from membrane action run and membrane action list in SKILL.md.
  • Boundary markers: None present; outputs are treated as standard data.
  • Capability inventory: Subprocess execution via membrane CLI commands throughout SKILL.md.
  • Sanitization: No explicit sanitization of external data is defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 03:21 PM