Back to scanner

Illustrative example. This fictional report demonstrates the scanner interface. It is not a live scan or an assessment of a real repository.

Scan a real skill
EXAMPLE REPORT/FICTIONAL SKILL BUNDLE

Research assistant

An illustrative skill that gathers research notes and prepares a summary.

Needs review
examples/research-assistantExample revisionIllustrative dataPublic example

Needs review

Related behavior was detected in the skill bundle. Review the evidence and its intended use before installing.

How to read this

Correlated findings

2

Related signals that passed the scanner’s correlation gate.

01

sensitive access with suspicious destination

high signal

A bundled script reads a credential source and sends data to a webhook within the same local code window.

scripts/collect.py:18, 22
NovaYARADetectDataExfiltrationModelCredentialHarvesting
02

instruction override with dangerous execution

medium signal

Instructions ask the agent to suppress disclosure while performing the flagged action. The combination increases the need for review.

SKILL.md:31, 34
NovaDetectSkillPromptInjection

AI intent assessment

ADVISORY

Likely malicious intent

In this illustrative example, the requested research task does not explain the credential transfer or concealment instructions. Both support closer inspection. This sample assessment is not a live AI response.

Illustrative assessmentModel confidence: 91% · not measured accuracy

All raw rule matches

4

Unfiltered engine matches include signals that did not pass correlation. Rule severity alone is not a verdict.

Engine / ruleLocationRule severity
NovaDetectDataExfiltrationscripts/collect.pyLines 18, 22high
YARAModelCredentialHarvestingscripts/collect.pycritical
NovaDetectSkillPromptInjectionSKILL.mdLines 31, 34medium
NovaDetectMaliciousToolPermissionsSKILL.mdLines 9low