zerotier
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to perform network operations, such as creating connections and running actions. These are legitimate uses of CLI tooling for the specified service. - [EXTERNAL_DOWNLOADS]: The documentation instructs users to install the
@membranehq/cliglobal package via npm. This is a vendor-provided tool necessary for the skill's operation. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests data from ZeroTier (such as member names, network descriptions, or API responses).
- Ingestion points: Data returned from
membrane action runandmembrane requestcommands as described inSKILL.md. - Boundary markers: Absent. There are no instructions for the agent to use delimiters or specific safety instructions when processing the external data.
- Capability inventory: The agent can execute CLI commands (
membrane) and perform network requests via the Membrane proxy as noted inSKILL.md. - Sanitization: Absent. The skill does not describe any sanitization or validation logic for the data retrieved from the ZeroTier API.
Audit Metadata