Workflow Automator

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes workflows that process untrusted data from external sources, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Pattern 2 (Issue Triage), Pattern 5 (Customer Onboarding), and Workflow 3 (Webhooks) involve reading data from GitHub issues, user signups, and external event triggers.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate untrusted content from the agent's core instructions.
  • Capability inventory: The skill utilizes capabilities for creating GitHub Actions, configuring webhooks, and sending Slack/Discord notifications.
  • Sanitization: No explicit sanitization or validation steps are provided to prevent embedded instructions in external data from influencing the agent.
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate and implement custom automation scripts and configuration files (GitHub Actions, Node/Python scripts). While standard for automation tasks, these represent a high-impact capability that requires careful oversight when the generation logic is influenced by external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:43 AM
Security Audit — agent-trust-hub — Workflow Automator