System prompt and context leakage
Asks for hidden instructions and flags the answer only when instructions actually come back.
Check method
Asks for hidden instructions and flags the answer only when instructions actually come back.
Possible evidence type
Live observation when the check is compatible and authorized. This description does not mean your platform has been tested.
Access and limitations
Website address. Actual results and checks not run appear in your report. A check with no finding does not guarantee the absence of risk.
Concrete scenario
A model returns part of its internal instructions when asked about its role.
What to inspect
Identify whether the returned text is genuinely internal and whether it includes sensitive values. Similar generic text is not reliable proof of a leak.
Remediation approach
Do not put secrets in system instructions. Restrict disclosures while recognizing that hidden instructions are not a credential store.
Separate instructions from untrusted content
An LLM may process user text, retrieved documents, tool output and application instructions in the same context. Content that looks like an instruction can therefore influence an answer. A suspicious answer is not automatically a data leak or an action: record exactly what changed and whether sensitive data or tools were involved.
- List input sources: user messages, documents, retrieval, history and tool results.
- Identify which instructions and secrets are placed in the model context.
- Distinguish a changed answer from a demonstrated confidential disclosure or unauthorized tool call.
Build layered protections
A stronger prompt is not a complete security boundary. Enforce tool permissions and data access outside the model, minimize what it can see, and validate its output before using it as executable code, HTML or a trusted decision.
- Remove credentials and unnecessary confidential material from context.
- Apply identity-scoped retrieval and allowlisted tool operations.
- Require approval for consequential actions and retain regression tests for known bypasses.
References
OWASP LLM07 · OWASP LLM02
Sources and further reading
These publications describe related practices and standards. They do not certify your platform or imply that Hackaiz executes every documented method.