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
membraneCLI 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/clipackage 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 runormembrane request. - Boundary markers: None present.
- Capability inventory: Execution of shell commands through the
membraneCLI tool. - Sanitization: No specific sanitization or filtering of article content is documented.
Audit Metadata