Security audit
Ai Writing Quality Check
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward remote writing-quality checker that sends user-provided text to AgentPMT for banned-phrase analysis.
Install only if you are comfortable sending the checked writing content to AgentPMT and potentially using its paid account or x402 payment setup. Do not include secrets, wallet keys, payment headers, or highly confidential copy in tool inputs.
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
63/63 vendors flagged this skill as clean.