AI Application Vulnerability Testing vs Web Scanning
Guide · 2023-05-30 · 6 min read · FilterPrompt Security Team
Distinguish prompt-based LLM vulnerability tests from web DAST and code scanning; test authorized AI endpoints and review model response evidence.
FilterPrompt is AI Security Testing & Vulnerability Scanner. It submits adversarial prompts to a connected LLM or AI application, analyses model responses, identifies vulnerabilities and generates reports with test evidence. It does not block live traffic, redact customer requests or act as a firewall.
Not every AI-powered scanner tests AI applications
A web DAST scanner probes web behavior such as access controls and injection into application code. SAST analyses source code. An LLM scanner sends adversarial prompts and evaluates model behavior. FilterPrompt is the latter; it does not replace web or source-code testing.
Choose representative test cases
- Direct instructions that try to override the assistant’s policy.
- Indirect instructions placed in synthetic retrieval content.
- Jailbreaks that attempt to bypass refusal behavior.
- Requests for protected synthetic data or system-only canaries.
- Unsafe response or tool-use scenarios in an isolated sandbox.
Evidence before conclusions
Record which endpoint was tested, the submitted prompt, the full model response, configuration and evaluation reason. A finding needs review in application context. A refusal does not establish correct retrieval permissions, and a safe base-model answer does not prove downstream code handles output safely.
Run an authorized assessment with FilterPrompt
- Create an account and connect an LLM using your own provider credentials. Use an authorized staging target and synthetic data.
- Choose a scan suite and review the probe selection and credit estimate. Test your application endpoint when you need coverage of its retrieval, tools and safeguards.
- Run the tests. FilterPrompt sends adversarial prompts and evaluates the responses against the selected criteria.
- Open the report and inspect each failing prompt, response, severity and evaluation reason. Manually confirm important findings; mark false positives with a reason when appropriate.
- Record remediation work with an owner in your existing issue tracker. Make changes in your application and retest the affected cases.
What a scan can and cannot establish
Results describe the tested endpoint, configuration and prompts at that point in time. A passing scan is not a guarantee of security, certification or legal compliance. Testing a raw provider model does not test the access controls, retrieval sources or tools in your application. Test limits and provider costs must be agreed before running an assessment.