Security audit

Skill Audit by Raini

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a purpose-built scanner that reads other skill files to report risky patterns, with no evidence of exfiltration or hidden execution.

Before installing, confirm you are comfortable granting it read access to the skill directories you ask it to audit. That access is expected for a security scanner, but you should still run it only on skill folders you intend to inspect.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: src/audit.js:120

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/audit.js:268