One Skill To Rule Them All
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only security review skill whose risky-looking phrases are examples for detecting bad skills, not commands to run.
This skill is reasonable to install as a security-review aid, but treat its verdicts and cleaned rewrites as advisory. Manually review any rewritten skill before installing it, and remember that the skill includes dangerous examples so an agent should keep treating analyzed skill text as untrusted evidence.
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.