Security audit
Git Commit Cn
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple Git commit-message helper that reads staged changes and suggests a Chinese Conventional Commits message without hidden execution or persistence.
Install only if you are comfortable with the agent reading staged Git diffs, which may include sensitive code or secrets if you accidentally staged them. The skill also includes promotional affiliate links in its report template, but they are displayed text rather than hidden network behavior.
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.