fidel-api

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is an official vendor resource required to use the skill and does not represent an unverified dependency.
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI tool to manage API connections and execute actions. These operations are standard for the platform and are limited to the vendor's documented ecosystem.
  • [PROMPT_INJECTION]: The skill processes external data from the Fidel API, which introduces a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through API responses from endpoints like list-transactions, get-card, and list-programs.
  • Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to encapsulate data from the API.
  • Capability inventory: The skill can execute shell commands via the membrane CLI and perform authenticated network requests via the membrane request command.
  • Sanitization: There is no evidence of data validation or sanitization being applied to the API responses before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 02:31 PM