acuity-scheduling
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI tool globally using the command
npm install -g @membranehq/cli@latest. This is a vendor-provided tool used to manage the integration lifecycle. - [COMMAND_EXECUTION]: The skill relies on executing shell commands via the
membraneCLI to perform various tasks, includingmembrane loginfor authentication,membrane connectionfor account management, andmembrane actionfor data operations. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its ingestion of external data from the Acuity Scheduling API.
- Ingestion points: Data enters the agent's context through the
intentparameter in theaction listcommand and via the JSONinputandoutputof various actions inSKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to treat external data as untrusted or to ignore instructions embedded within retrieved content.
- Capability inventory: The skill possesses the capability to execute shell commands and perform arbitrary network requests via
membrane action runandmembrane requestacross all its functional scripts. - Sanitization: The instructions do not describe any mechanisms for sanitizing or validating external data before it is interpolated into agent prompts or CLI commands.
Audit Metadata