Anti-Slop
Security checks across malware telemetry and agentic risk
Overview
Anti-Slop is an instruction-only review skill that asks the agent to check writing and claims for quality, evidence, and originality without requesting installs, secrets, persistence, or unrelated access.
This skill is reasonable to install if you want stricter review of AI-generated work. Be aware that when used on code or PR claims, it may encourage the agent to inspect files and run verification commands using whatever permissions the agent already has, so use it in appropriately scoped workspaces.
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
65/65 vendors flagged this skill as clean.