CalvinBackup/www-project-ai-testing-guide
1
0
Fork 0
mirror of https://github.com/OWASP/www-project-ai-testing-guide.git synced 2026-07-15 23:47:19 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update AITG-APP-06_Testing_for_Agentic_Behavior_Limits.md

Browse Source
This commit is contained in:
Matteo Meucci
2025-11-23 13:35:38 +01:00
committed by GitHub
parent bf552d20f1
commit a64b7a1c04
1 changed files with 5 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Document/content/tests/AITG-APP-06_Testing_for_Agentic_Behavior_Limits.md
+5 -10
View File
@@ -167,16 +167,11 @@ In 2023, GPT-4, when tested by ARC, hired a human on TaskRabbit to solve a CAPTC
- Sandbox high-risk tools and isolate agent memory and communication channels.
### Suggested Tools
- **Galileo Agentic Evaluations**: Monitors and evaluates agent behavior.
- [https://www.galileo.ai/agentic-evaluations](https://www.galileo.ai/agentic-evaluations)
- **Giskard Red Teaming**: LLM-based red teaming for agent scenarios.
- [https://www.giskard.ai](https://www.giskard.ai)
- **BrowserART**: Tests browser-based agents for unsafe behavior.
- [https://github.com/scaleapi/browser-art](https://github.com/scaleapi/browser-art)
- **SafeAgentBench**: Benchmarks safe refusal on hazardous tasks.
- [https://arxiv.org/abs/2412.13178](https://arxiv.org/abs/2412.13178)
- **Agentic Security Scanner**: An open-source tool for scanning AI systems to detect vulnerabilities related to agentic behaviors.
- [https://www.star-history.com/blog/agentic-security](https://www.star-history.com/blog/agentic-security)
- **Galileo Agentic Evaluations**: Monitors and evaluates agent behavior - [Link](https://www.galileo.ai/agentic-evaluations)
- **Giskard Red Teaming**: LLM-based red teaming for agent scenarios - [Link](https://www.giskard.ai)
- **BrowserART**: Tests browser-based agents for unsafe behavior - [Link](https://github.com/scaleapi/browser-art)
- **SafeAgentBench**: Benchmarks safe refusal on hazardous tasks - [Link](https://arxiv.org/abs/2412.13178)
- **Agentic Security Scanner**: An open-source tool for scanning AI systems to detect vulnerabilities related to agentic behaviors - [Link](https://www.star-history.com/blog/agentic-security)
### References
- OWASP Top 10 for LLM – LLM06: Excessive Agency – [Link](https://genai.owasp.org/llmrisk/llm06-sensitive-information-disclosure/?utm_source=chatgpt.com)