Skills
skills/andrelandgraf/fullstackrecipes/using-workflows/Gen Agent Trust Hub

using-workflows

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): Detected surface for Indirect Prompt Injection. Ingestion points: The chatWorkflow function in SKILL.md accepts userMessage. Boundary markers: None identified in the provided snippets. Capability inventory: The workflow performs database writes and executes AI agents. Sanitization: No input sanitization is present beyond type assertion.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:23 PM