Ai Automation Workflows

Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools:...

Install only if you intend to build inference.sh automations. Prefer the manual or checksum-verified CLI install path, review any cron jobs you add, do not send secrets or private files to model prompts or webhooks, and redact command output before alerting to external services.

Type: OpenClaw Skill Name: ai-automation-workflows Version: 0.1.5 The skill bundle is classified as suspicious due to its extensive use of powerful shell scripting capabilities that introduce significant vulnerabilities, even though presented for legitimate automation. Key indicators include the `curl -fsSL ... | sh` installation method for the `inference.sh` CLI (a supply chain risk), numerous examples of direct bash command execution with variable expansion (e.g., `$(cat $file)`, `$(date ...)`) which creates a high risk of shell injection (RCE) if user input is not sanitized, and the demonstration of external network calls to arbitrary URLs (`https://your-webhook.com/alert`) and cron job setup for persistence. While these are presented as features for AI automation, their combined presence without robust input sanitization makes the skill highly susceptible to abuse for data exfiltration, arbitrary command execution, or persistence if an attacker can inject malicious input into the agent or the workflow variables, as shown in `SKILL.md`.