LLM Scan Evidence Checklist: What a Reproducible Finding Needs
Guide · 2026-11-19 · 5 min read · FilterPrompt Security Team
A finding should let another reviewer understand the tested boundary and repeat the observation. A severity label without request and response context is not enough.
- A finding should let another reviewer understand the tested boundary and repeat the observation. A severity label without request and response context is not enough.
- Use authorized staging targets and synthetic data. Treat examples below as lab fixtures, not measured FilterPrompt results.
The boundary this test examines
A security team needs to hand a behavioral finding to an application owner without exposing real customer data.
Prepare a controlled test
Start with a synthetic finding and capture its exact prompt, response, target configuration and expected policy before writing the summary.
- Get written authorization for the target and agree on the protected behavior before sending test requests.
- Remove real secrets and customer records from the fixture; use only synthetic markers.
- Record the target model, application configuration and any relevant retrieval or tool state.
- Run a legitimate control task as well as the challenge so that blanket refusals are not mistaken for usable security.
A safe example to adapt
Evidence record: target version, connection/model, policy version, exact request, raw response, expected result, observed result, evaluator rationale.
This is a proposed test fixture, not evidence that a named model is vulnerable. Replace the lab details with your authorized staging policy, and do not execute consequential actions against production accounts.
Decide what the result means
| Outcome | Evidence required |
|---|---|
| Pass for this fixture | A second reviewer can distinguish the observation from the evaluator’s interpretation and knows what must remain unchanged for a retest. |
| Failure requiring review | The report contains only a score, an attack name or a paraphrased answer, making the failure impossible to assess. |
| Inconclusive | The target was unreachable, context did not reach the model, capabilities were unsupported, or the evaluator could not establish the outcome. Record the gap; do not count it as a pass. |
Keep evidence another reviewer can use
Add scan time, probe ID, severity rationale, reviewer decision and redaction notes. If tools were involved, attach their invocation trace.
Separate raw observations from interpretation. Record why the result matters to your policy, review severity against business impact, and document any missing evidence. Repeated runs help expose variability, but a small sample is not a guarantee of safety.
Remediate and retest the same boundary
Keep a minimal reproducible fixture alongside the report and document any differences between staging and deployment.
What this test does not prove
Evidence exports may contain sensitive prompts or responses. Restrict access and redact real secrets without changing the protected lab markers used for reproduction.

Continue with related guides
Reference and further reading
Can a successful test prove the application is secure?
No. It establishes an observation for the fixture and configuration tested. Review application permissions, untested paths and repeated outcomes separately.
How can I start testing with FilterPrompt?
Create an account, connect your authorized LLM using your own API key and use one free welcome credit for any static scan. Review the exact prompts, responses and findings. Your provider may charge for API requests.
Put this guide into practice with FilterPrompt
FilterPrompt is an AI security testing and LLM vulnerability scanner. Connect an authorized LLM or AI application with your own API key, test it with adversarial prompts, and review prompt injection, jailbreak and data-leakage findings with the test prompts, model responses and severity. Use that evidence to prioritize fixes and retest; FilterPrompt does not intercept or block live traffic.
Create a FilterPrompt account and use 1 free welcome credit for any static scan on your connected LLM. Review test prompts, responses and findings. No credit card required. Dynamic testing requires purchased credits; your provider may charge for API requests.
