ClawHub

Reducing Entropy

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only refactoring guidance skill that openly encourages code simplification and deletion, with no hidden execution, credential access, persistence, or exfiltration behavior found.

Install only from a source you trust, preferably after reviewing or pinning the GitHub source. Use this skill on a branch, inspect all removals carefully, and run relevant tests before accepting code or test deletions.

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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This section explicitly encourages deleting code and tests as a default optimization strategy, but it does not require preserving behavioral guarantees, validating coverage, or warning the user about potential loss of functionality. In an agent skill, this can steer the model toward unsafe refactors that remove safeguards or regressions checks in pursuit of smaller code size.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill framing strongly biases toward aggressive code reduction ('ruthless simplification', 'bias toward deletion') without balancing instructions about reliability, safety, or maintaining required behavior. That context makes the skill more dangerous because it can cause an agent to prioritize code shrinkage over correctness, including removal of defensive checks, tests, or necessary structure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal