ClawHub
Back to skill

Security audit

Incremental Implementation

Security checks across malware telemetry and agentic risk

Overview

This skill is a coding workflow guide with no executable payload or data access, though users should notice its broad triggers and its advice to make frequent git commits.

Install only if you want coding agents to favor small, tested implementation slices and possibly create frequent git commits. Review the trigger list if you want tighter activation, and keep normal control over when commits are allowed.

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 trigger list contains broad, everyday phrases such as terms related to doing too much at once or scope creep, which can cause the skill to activate outside the author's intended context. Unintended invocation can override or steer an agent's behavior during unrelated tasks, creating prompt-routing risk and reducing operator control.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.