ClawHub
Back to skill

Security audit

Breweries

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward brewery lookup helper that queries a public API, with a caveat that the runnable script is fetched from an external GitHub repo rather than included in the reviewed files.

Install only if you are comfortable with a skill making public Open Brewery DB requests for brewery-related questions. Because the README points to executable scripts obtained through a GitHub clone that are not present in the reviewed artifact, inspect those cloned files before running or making them executable.

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
88% confidence
Finding
The skill encourages automatic use on broad natural-language prompts like 'When user asks about breweries' and maps common phrases directly to commands without requiring an explicit invocation boundary. This can cause over-triggering or unintended tool use in unrelated conversations, which is a real safety issue even though the underlying commands are low risk and read-only.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.