ClawHub
Back to skill

Security audit

Harness

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only agent-engineering knowledge skill with broad but disclosed activation guidance and no executable code or credential access found.

Install this if you want agent-first engineering guidance available during coding and architecture discussions. Be aware it may load for broad topics like codebase structure, context management, AGENTS.md, observability, and agentic tech debt; narrow or disable it if that becomes distracting.

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
89% confidence
Finding
The README states the skill 'loads automatically' for a wide set of topics, but it does not define precise trigger boundaries, exclusions, or matching rules. In an agent environment, broad auto-activation can cause the skill to be invoked in unintended contexts, leading to prompt/context injection of irrelevant guidance, increased attack surface, and potential interference with higher-priority instructions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.