ClawHub
Back to skill

Security audit

Inception Token Optimizer

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Inception Labs token-cost optimization guide with small local helper scripts and no evidence of hidden access or harmful behavior.

This is reasonable to install as a local optimization aid. Before using its cache helper, consider whether prompts or responses may contain confidential data, since cached prompt-response pairs remain in process memory until evicted or cleared.

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
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The markdown recommends prompts such as "Concise answers. French." and "Réponds en < 100 mots," which prescribe a specific language/locale. This is a natural-language policy concern because the skill does not present French as optional or require explicit user preference before enforcing it.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal