Security audit
contrarian-and-opinion
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed writing aid for shaping genuine opinion content, with clear limits against fabricated ragebait, defamation, and misinformation.
Before installing, understand that this skill is intended to help draft public-facing opinion content. It appropriately says the human owns the stance and publish decision, so users should still review factual claims, legal/reputational risk, and brand fit before publishing.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.