ClawHub
Back to skill

Security audit

Token Saver For Programmer

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only token-compression skill with disclosed broad auto-activation, so users should review shortened outputs but there is no evidence of hidden, privileged, or malicious behavior.

Install only if you want an assistant to automatically condense technical material. Review outputs before using them in production code, configs, debugging, security logs, or prompts where exact wording and full context are important.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill is configured to auto-activate on very generic content types like code, log, config, and prompt, which are common in normal developer workflows. This can cause the skill to trigger unexpectedly and transform user input without explicit consent, potentially removing important context, altering edge-case logic, or degrading security-relevant details in code, configs, or logs.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.