neetokb

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as searching for connectors, connecting to workspaces, and running actions against the NeetoKB API. These commands are part of the intended integration workflow.- [EXTERNAL_DOWNLOADS]: The documentation instructs the user to install the @membranehq/cli package via NPM. This package is an official tool from the vendor used to facilitate the integration.- [PROMPT_INJECTION]: The skill processes content from external NeetoKB articles, which serves as a potential surface for indirect prompt injection. If an article contains instructions designed to manipulate the agent, it could lead to unexpected behavior.
  • Ingestion points: NeetoKB article content retrieved via membrane action run or membrane request.
  • Boundary markers: None present.
  • Capability inventory: Execution of shell commands through the membrane CLI tool.
  • Sanitization: No specific sanitization or filtering of article content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 05:58 PM