The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the vendor's command-line interface tool (@membranehq/cli) globally via the npm registry, which is a well-known service.
[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the membrane CLI to manage authentication, establish connections to external services, and perform API operations.
[INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing data from Zoho Forms, which introduces a potential surface for indirect prompt injection if the records contain malicious instructions intended to influence the agent's behavior. 1. Ingestion points: Data is retrieved from the Zoho Forms API through the 'membrane action run' and 'membrane request' commands as described in SKILL.md. 2. Boundary markers: The skill documentation does not specify the use of delimiters or instructions to ignore embedded commands within the processed records. 3. Capability inventory: The skill utilizes the membrane CLI to perform actions, list connection details, and send raw requests to external APIs. 4. Sanitization: No explicit sanitization or content validation procedures are mentioned for the data fetched from Zoho Forms prior to its processing by the agent.

zoho-forms