The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a set of provided Node.js scripts to perform platform operations like fetching graphs, managing triggers, and deploying functions. This execution model is the standard interface for the skill's functionality.
[EXTERNAL_DOWNLOADS]: The instructions include a standard dependency installation step via npm i. No unverified or suspicious remote code downloads were detected.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes data from external, untrusted sources.
Ingestion points: External data enters the agent context through query-rows.js (database records) and get-execution.js (WhatsApp execution details and message content).
Boundary markers: Absent. The instructions do not specify the use of delimiters or provide the agent with warnings to ignore instructions embedded within retrieved data.
Capability inventory: The agent can execute shell commands via the included Node scripts and possesses the ability to deploy and invoke arbitrary code on the platform runtime using deploy-function.js and invoke-function.js.
Sanitization: Absent. There is no indication of sanitization, validation, or filtering of the content retrieved from external sources before it is processed by the agent.

automate-whatsapp