Security audit
create-docs-skill
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed workflow for turning documentation websites into reusable skills, with no hidden or unrelated behavior found.
Install this if you want an agent workflow for creating skills from documentation sites. Expect it to use web/GitHub access and local file operations while building a skill, and review generated skill changes before replacing or merging with an existing skill.
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.