ClawHub
Back to skill

Security audit

report

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed report-automation helper that can save report data locally and send configured reports externally, so it is usable but should be installed only when those behaviors are intended.

Install this only if you want the agent to create ~/report, retain report history locally, read the data sources you configure, and optionally send report contents to Telegram, email, or webhook destinations you trust. Use chat or file delivery for sensitive reports and avoid configuring broad local paths or external channels unless needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is broad enough to match generic requests about analysis, reporting, statistics, and visualization, which can cause over-triggering in unrelated contexts. In an agent with read/exec/write tools, that increases the chance the skill is invoked without the user understanding it may create files, schedule work, or send data externally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents creation and modification of local files under ~/report without an early, prominent warning at the top of the skill. Users may invoke it expecting analysis only, while the skill can persist configs, logs, and generated reports on disk, which is risky when reports may contain sensitive business data.

External Transmission

Medium
Category
Data Exfiltration
Content
sources:
  - type: api
    env: STRIPE_API_KEY
    endpoint: "https://api.stripe.com/v1/charges"
    params:
      created.gte: "last_week_start"
      created.lt: "today"
Confidence
90% confidence
Finding
https://api.stripe.com/

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.