Capability Composition Analyzer
Security checks across malware telemetry and agentic risk
Overview
This skill is a defensive, documentation-only analyzer for spotting risky combinations of other skills, with no evidence of hidden execution or data access.
This appears safe to install as a security-analysis helper. Its examples mention exfiltration and remote code execution defensively, not as instructions to perform them. The only caveat is the metadata declaring curl and python3 even though no visible workflow uses them, so users should provide only the skill lists or capability metadata they intend to analyze.
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.