ClawHub
Back to skill

Security audit

Hot Skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward ClawHub trend-monitoring tool that fetches public skill data and stores local state only for its advertised alerts.

Install this if you want a local CLI that periodically checks ClawHub trends. Expect outbound requests to clawhub.ai when commands run, local files under ~/.skill-surge-notifier, and recurring background checks only if you add the cron entry yourself. Do not put secrets in the profile description or keywords.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill documentation describes capabilities that use network access and environment-controlled behavior, but it does not declare permissions or provide an explicit capability/consent model. This can cause an agent or user to run code that fetches remote data and reads environment configuration without clear awareness of the scope of access.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill states that it writes persistent state under the user's home directory, but it does not prominently warn that local files will be created and updated. Hidden persistence is a security and trust concern because users may not realize the tool is modifying disk state or leaving artifacts behind.

Session Persistence

Medium
Category
Rogue Agent
Content
- State is stored in `~/.skill-surge-notifier/state.json`. The first run seeds the baseline; growth % appears from the second run onward.
- All output is printed to stdout. When used inside an agent, the agent must capture the CLI output to surface alerts in chat.
- To run automatically, add to crontab (`crontab -e`):

```bash
0 */4 * * * node {baseDir}/cli.js check >> ~/.skill-surge-notifier/surge.log 2>&1
Confidence
91% confidence
Finding
crontab -e

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
fetch_trending.js:21