zoho-creator
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is a vendor-owned CLI tool required for the skill to interact with the Membrane platform.
- [COMMAND_EXECUTION]: The skill executes shell commands using the membrane CLI to perform authentication (membrane login), manage connections (membrane connection ensure), and run API actions (membrane action run). These are standard operational commands for this platform.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Zoho Creator, which serves as a potential attack surface.
- Ingestion points: Data enters the agent context through actions such as get-records, get-record-by-id, and direct proxy requests performed in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided documentation.
- Capability inventory: The skill possesses the capability to execute shell commands via the Membrane CLI and perform network operations through the Membrane proxy.
- Sanitization: There is no explicit evidence of sanitization or validation of the data retrieved from Zoho Creator before it is processed by the agent.
Audit Metadata