ClawHub
Back to skill

Security audit

Yelp

Security checks across malware telemetry and agentic risk

Overview

This Yelp skill is a disclosed Yelp research helper with optional API use and local notes, and I found no evidence of hidden or destructive behavior.

Safe to install for Yelp research if you are comfortable sharing relevant search details with Yelp. Keep your Yelp API key out of notes, confirm before using phone numbers or exact addresses in API calls, and periodically review or delete ~/yelp/ if you do not want old local preferences reused.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation criteria are broad enough that the skill could trigger on loosely related requests such as general local recommendations, business research, or review summaries without clear opt-in boundaries. Over-broad activation can cause unintended tool use, unnecessary data access, and routing of user requests into this skill when a different workflow would be safer or more appropriate.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
curl -sS -H "Authorization: Bearer ${YELP_API_KEY}" \
  "https://api.yelp.com/v3/businesses/search/phone?phone=%2B14159083801" \
  | jq '{id, alias, name, location, phone}'
```
Confidence
80% confidence
Finding
https://api.yelp.com/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.