Security audit
Overllm
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent local static-linter wrapper that reads code to report unnecessary LLM calls, with only a disclosed optional pip install and opt-in file edits.
Install only if you are comfortable allowing the agent to install and run the external overllm Python package. Normal scans should be read-only; review before using --fix or --unsafe-fixes because those modes can edit files.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.