workflow-business-evaluation

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a coordinator for a sequential workflow (/web-research to /workflow-end). It does not contain any executable scripts, network requests to untrusted domains, or attempts to access sensitive local files.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting untrusted user input to provide context for the workflow. However, this is a standard functional requirement for a research agent.
    • Ingestion points: User prompt used as context for the /workflow-start command.
    • Boundary markers: Absent; user input is passed directly to the workflow engine.
    • Capability inventory: Accesses research tools (/web-research, /deep-research) and analysis modules.
    • Sanitization: None explicitly defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM