Chain Of Custody

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly described report-generation API, but users should treat the case, evidence, and identity data it sends as sensitive.

Use sanitized data for testing. Before submitting live investigations, confirm your organization allows sharing case numbers, evidence descriptions, collection locations, personnel names, hashes, and requester identifiers with this API provider, and verify the provider's retention, access-control, logging, and deletion practices.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly documents collection and submission of highly sensitive investigative and personal data, including case details, evidence metadata, user identity, and email address, but provides no privacy, retention, confidentiality, or legal-handling warnings. In a forensic/legal context, this increases the chance that users transmit regulated or privileged evidence data to a third-party API without understanding disclosure, jurisdiction, or compliance risks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal