ClawHub
Back to skill

Security audit

Random Coffee Outreach

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local, consent-focused helper for matching opt-in participants and preparing review packets, with no evidence of hidden outreach, credential use, or data exfiltration.

Install only if you intend to use it with consented participant data. Keep generated CSVs, reports, packets, and logs local/private, review drafts before sending anything, and confirm both people opt in before sharing names, handles, links, or detailed context.

SkillSpector

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
93% confidence
Finding
The invocation guidance includes broad phrases such as 'warm networking' and 'founder/operator matching' that could cause the skill to be selected in loosely related conversations rather than only when the user explicitly wants this workflow. In a people-matching and outreach context, accidental invocation is more sensitive because it can lead the agent to process participant/contact data or generate outreach artifacts in situations where the user did not clearly request that behavior.

Static analysis

No suspicious patterns detected.