Security audit
Jd Writing
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for writing Chinese job descriptions, with no evidence of hidden execution, data theft, or unsafe behavior.
Safe to install for JD-writing assistance. Review any company, compensation, candidate-screening, or hiring-strategy details before sharing them, especially if you later ask the agent to update the skill’s reusable guidance.
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.