mautic
Pass
Audited by Gen Agent Trust Hub on Nov 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI global package (
@membranehq/cli) from the npm registry. This package is the official tool provided by the vendor (membrane) for managing connections and actions. - [COMMAND_EXECUTION]: The instructions rely on executing shell commands through the Membrane CLI (
membrane login,membrane connection ensure,membrane action run) to perform tasks and retrieve data. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Mautic API, creating a surface for indirect prompt injection if retrieved content (e.g., contact notes, email bodies, or campaign descriptions) contains adversarial instructions.
- Ingestion points: Data is retrieved from Mautic via
membrane action run(e.g.,get-contact,list-emails) andmembrane requestas described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific system prompts to warn the agent about potentially untrusted content in API responses.
- Capability inventory: The skill includes write capabilities such as
create-contact,update-contact, and the ability to send arbitrary HTTP requests viamembrane request(POST, PUT, DELETE). - Sanitization: There is no evidence of sanitization or strict schema validation performed on the external data before it is presented to the agent's context.
Audit Metadata