Security audit
Add to Awesome Agent-Native Services
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only contribution guide for adding entries to a public catalog, with expected web research, local file edits, and reviewed GitHub workflow steps.
Before installing, be comfortable with an agent helping edit a local Git repository and prepare public GitHub content. Review external onboarding pages, generated diffs, shell/git commands, issue text, and PR content before allowing submission.
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.
Static analysis
No suspicious patterns detected.