knit

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the @membranehq/cli tool to interact with Knit. This is the standard method for skills on the Membrane platform to manage connections and execute actions.- [EXTERNAL_DOWNLOADS]: Installation of the @membranehq/cli global package is required. This package is an official tool from the platform vendor used to bridge the agent with the Membrane environment.- [PROMPT_INJECTION]: The skill is designed to process data from Knit threads and messages. While this constitutes a surface for indirect prompt injection, it is the core functionality of the skill and no instructions are present to execute the retrieved data as commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:45 PM