ClawHub

Cybersecurity

Security checks across malware telemetry and agentic risk

Overview

This cybersecurity helper is purpose-aligned and locally scoped, though users should be deliberate about what sensitive security context they let it remember.

Before installing, decide whether this skill should activate only when explicitly requested or may join broader security-related conversations. Keep ~/cybersecurity/ private, do not store secrets, raw logs with sensitive data, tokens, or private keys there, and periodically clear stale incident notes or scope assumptions.

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 (2)

Vague Triggers

Low
Confidence
85% confidence
Finding
This markdown file is in scope for vague-trigger review. The phrase 'Use when the user needs cybersecurity help across incident triage, threat modeling, control review, vulnerability prioritization, secure design discussions, tabletop prep, or executive-ready risk communication' is expansive and does not define clear boundaries or exclusions, which can make invocation conditions ambiguous for general security-related conversations.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The setup instructions define activation using broad topics like 'incidents, vulnerabilities, alerts, secure design, abuse cases, or risk reviews' and ask the system to learn whether to 'jump in proactively on obvious security gaps.' This lacks explicit trigger phrases, exclusion conditions, or negative examples, so the skill may activate in many ordinary discussions that mention security concepts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal