action-builder

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli npm package. This is an official command-line interface provided by the vendor for managing integrations and authentication.\n- [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as user authentication (membrane login), resource searching (membrane search), and executing specific automation tasks (membrane action run).\n- [PROMPT_INJECTION]: The skill processes data returned from Action Builder API endpoints, which represents an indirect prompt injection surface where external data enters the agent context.\n
  • Ingestion points: Output from commands including membrane action list, membrane action run, and membrane request.\n
  • Boundary markers: Not present; the skill does not define delimiters to separate tool output from instructions.\n
  • Capability inventory: The skill has the ability to execute actions and make arbitrary API requests through the membrane tool.\n
  • Sanitization: No explicit sanitization or validation of the ingested API data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 11:25 PM
Security Audit — agent-trust-hub — action-builder