skills/catena-labs/skills/catena-cli/Gen Agent Trust Hub

catena-cli

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes frequent use of npx -y catena-cli, which downloads and executes the latest version of the catena-cli package from the npm registry. This is the official tool provided by the vendor (catena-labs) and is considered a legitimate dependency for the skill's purpose.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands to interact with the Catena Bank API. This includes operations for linking agents, listing accounts, and initiating financial transactions. These commands are necessary for the skill to function as a banking interface.
  • [DATA_EXFILTRATION]: The skill involves handling sensitive financial data, such as account IDs and transaction histories. However, all data transmission occurs via the official CLI to the vendor's documented API endpoint (api.catena.com). The feedback command allows sending text messages to the vendor's support team as an intended feature.
  • [PROMPT_INJECTION]: The skill instructions do not contain any patterns intended to bypass agent safety filters or override system instructions. The language used is instructional and specific to the operation of the banking CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:37 PM
Security Audit — agent-trust-hub — catena-cli