Translational Gap Analyzer

Security checks across malware telemetry and agentic risk

Overview

This is a local scientific report generator whose optional file output is disclosed and aligned with its purpose.

Install only if you want a local Python helper for heuristic translational-risk reports. Use explicit workspace output paths, avoid pointing --output at important existing files, and treat the generated scores as research support rather than medical, regulatory, or clinical advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill documentation indicates the script can write output files (`--output`, generated artifacts) while no explicit permissions are declared. That mismatch is a real security concern because an agent or reviewer may assume the skill is read-only when it can modify the filesystem, increasing the chance of unintended overwrites or writes outside the intended workspace if the implementation is weak.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal