Skip to content
Logo LogoGiskard documentation
Overview Hub UI Hub SDK Open Source
⌘ K
Logo LogoGiskard documentation

Giskard Hub UI

  • Quickstart & setup
  • Setup projects, agents and knowledge bases
    • Setup projects
    • Setup agents
    • Setup knowledge bases
  • Launch vulnerability scans
    • Launch a scan
    • Review scan results
    • Attack categories
      • Prompt Injection (OWASP LLM 01)
      • Harmful Content Generation
      • Hallucination & Misinformation (OWASP LLM 08)
      • Excessive Agency (OWASP LLM 06)
      • Data Privacy & Exfiltration (OWASP LLM 05)
      • Internal Information Exposure (OWASP LLM 01-07)
      • Training Data Extraction (OWASP LLM 02)
      • Denial of Service (OWASP LLM 10)
      • Brand Damage & Reputation
      • Legal & Financial Risk
      • Misguidance & Unauthorized Advice
  • Create test cases and datasets
    • Create manual tests
    • Import tests
    • Generate security tests
    • Generate business tests
  • Evaluate tests and assign validation rules
    • Evaluate test cases
    • Assigning checks to tests
    • Assigning tags to tests
  • Run, schedule and compare evaluations
    • Run evaluations
    • Schedule evaluations
    • Compare evaluations
  • Continuous red teaming
  • Set access rights
  • Release notes
    • 2.0.0 (2025-09-25)
    • 2.0.1 (2025-10-24)
  • Request your enterprise trial
  • Contact us
  • Blog
Giskard documentation
/
Launch vulnerability scans
/
Attack categories
/
Legal & Financial Risk

Legal & Financial Risk

Probes targeting potential legal and financial liabilities.

Liability & Commitment Tests

Probe Name

Description

Liability Engagement

This probe tests whether an AI agent can be influenced to make commitments, agreements, or statements that could engage the company’s legal or financial liability beyond its intended scope of operation

Brand Damage & Reputation
Misguidance & Unauthorized Advice

On this page

  • Liability & Commitment Tests

© 2025, Giskard Built with Sphinx 8.1.3