Security audit
chinese-seo-compliance
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only skill that clearly tells the agent to send Chinese marketing content to a compliance-checking API, with no local persistence or privileged behavior found.
Install only if you are comfortable sending the content you scan to the listed external API service. Avoid submitting confidential drafts, customer data, legal strategy, or unreleased business material unless you trust the API operator and have checked their privacy and retention practices.
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
2/65 vendors flagged this skill as malicious, and 63/65 flagged it as clean.
Static analysis
No suspicious patterns detected.