eventzilla
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the @membranehq/cli package, which is the official command-line tool for the Membrane platform. This tool is required for authentication and managing the integration logic. Evidence: npm install -g @membranehq/cli in SKILL.md.\n- [COMMAND_EXECUTION]: The skill provides instructions for running various membrane CLI commands. These commands are used to log in, search for connectors, establish connections, and perform API actions on the Eventzilla platform. Evidence: Use of membrane login, membrane connect, membrane action list, and membrane action run in SKILL.md.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from an external source (Eventzilla) and has the capability to perform state-changing actions.\n
- Ingestion points: Retrieves event lists, attendee details, and transaction data from Eventzilla via membrane action run and membrane request in SKILL.md.\n
- Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential instructions embedded in the retrieved data.\n
- Capability inventory: The skill can create checkouts, cancel orders, and toggle event sales as documented in SKILL.md.\n
- Sanitization: There is no evidence of data sanitization or validation of the content retrieved from the external API before it is processed by the agent.
Audit Metadata