Security audit
sense-wonder
Security checks across malware telemetry and agentic risk
Overview
This skill appears to provide philosophical reference content for agents, with no evidence of hidden access, persistence, credential use, or destructive behavior.
Install this if you want your agent to use this philosophy and alignment-oriented context. The main consideration is ordinary supply-chain trust because the skill installs code from an external PyPI package rather than containing all runtime code in the artifact.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.