ClawHub
Back to skill

Security audit

Governance Explainer

Security checks across malware telemetry and agentic risk

Overview

This appears to be a governance guidance skill with only a trigger-precision concern and no evidence of hidden code, credential use, persistence, or destructive behavior.

This skill looks safe to install based on the available evidence. Users should treat its answers as governance guidance only when they are explicitly asking about DAO rules, proposals, votes, or related policy, and publishers should tighten the triggers to avoid accidental activation in unrelated conversations.

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
90% confidence
Finding
The trigger phrases "what is allowed" and "is this permitted" are very broad, natural-language queries that can overlap with many unrelated user requests. This can cause the skill to activate unintentionally, leading to incorrect routing or authoritative-sounding governance guidance being injected into conversations where it was not explicitly requested.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.