salesmsg
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform actions, manage connections, and login. These are standard operations for the Membrane platform. - [EXTERNAL_DOWNLOADS]: Fetches
@membranehq/clifrom the NPM registry. This is the official command-line interface for the Membrane platform, provided by the vendor. - [PROMPT_INJECTION]: Potential surface for indirect prompt injection when handling Salesmsg data.
- Ingestion points: Data is retrieved from Salesmsg (e.g., conversations, templates) using the
membrane action runcommand inSKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters for external content.
- Capability inventory: The skill can execute shell commands via the
membraneCLI and create new actions dynamically. - Sanitization: Absent; there is no evidence of filtering or validation of the content retrieved from Salesmsg before it is processed by the agent.
Audit Metadata