agentskills-io
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Agent Skills authoring and validation helper; its remote validator and local version-bump commands are user-run and purpose-aligned.
Install if you are comfortable running a validator fetched from GitHub. Prefer one-shot uvx use or pin and review the upstream validator before permanent installation, and inspect git diffs after using the version-bump script.
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.
