financialforce

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @membranehq/cli tool globally using npm. This is a vendor-supplied utility necessary for the integration.
  • [COMMAND_EXECUTION]: Utilizes the 'membrane' command-line interface to perform setup, connection management, and data retrieval from FinancialForce. These operations are core to the skill's intended functionality.
  • [PROMPT_INJECTION]: The skill processes external data from FinancialForce, which establishes a potential surface for indirect prompt injection if the retrieved content contains instructions for the agent.
  • Ingestion points: FinancialForce record data accessed via the 'membrane' CLI in SKILL.md.
  • Boundary markers: Not explicitly defined in the processing instructions.
  • Capability inventory: Shell execution of 'membrane' CLI commands for data management.
  • Sanitization: Relies on default platform handling for external data output without explicit filtering logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 12:41 PM