chatwoot
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the Membrane CLI (
@membranehq/cli) from the official NPM registry to facilitate the integration. - [COMMAND_EXECUTION]: The instructions involve executing several shell commands using the
membraneCLI, includingmembrane login,membrane connection ensure,membrane action list, andmembrane action run. These commands are used to manage authentication and interact with the Chatwoot API. - [INDIRECT_PROMPT_INJECTION]: The skill uses a natural language query via the
--intentflag in themembrane action listcommand to discover available API actions. - Ingestion points: The
--intentflag inSKILL.md(e.g.,membrane action list --intent "QUERY"). - Boundary markers: None explicitly defined for the search string.
- Capability inventory: Includes network access, connection management, and execution of Chatwoot API actions via the CLI.
- Sanitization: The skill relies on the CLI's internal processing of the search string.
Audit Metadata