twist
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/clipackage globally via NPM. This tool is the official command-line interface for the Membrane platform, which is the vendor for this skill. - [COMMAND_EXECUTION]: The instructions direct the agent to execute several shell commands using the
membraneCLI, including login procedures, action discovery, and executing requests to the Twist API. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from an external source (Twist API) that may contain malicious instructions.
- Ingestion points: Data from the Twist API enters the agent's context via the
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided documentation.
- Capability inventory: The skill provides the ability to perform network operations through the
membrane requestcommand. - Sanitization: The skill does not describe any sanitization or validation steps for the data returned by the API before it is processed by the agent.
Audit Metadata