revamp-crm

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via npm. This is a vendor-owned resource used for interacting with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill employs the membrane CLI for core operations, including authentication (membrane login), connecting to CRM elements (membrane connect), and executing actions (membrane action run).
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes data retrieved from the Revamp CRM API.
  • Ingestion points: Data returned from CRM actions and proxied API requests (SKILL.md).
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Execution of local CLI commands (membrane) and proxied network operations.
  • Sanitization: No explicit sanitization or validation of the ingested external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:00 AM