ClawHub
Back to skill

Security audit

guest-circuit

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed podcast-guest research workflow that uses public web searches and writes a constrained markdown report.

Install this if you want agents to run public podcast-appearance research and create saved circuit reports. Be aware that using it will send guest names and anchor facts to search or podcast tools, may use multiple web calls or subagents, and will write a markdown report unless you direct otherwise.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill declares broad natural-language invocation phrases such as "research X before outreach," which can overlap with ordinary user requests and cause the agent to auto-invoke a web-heavy workflow without sufficiently explicit user intent. This is dangerous because it can trigger unnecessary external searches and downstream actions in contexts where the user only wanted lightweight advice or discussion, increasing privacy, cost, and unintended tool-use risk.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs the agent to write a report to `circuit/{name-slug}-{YYYY-MM-DD}.md` without an upfront user-facing warning or confirmation that a file will be created. While the write target is relatively constrained, silent file creation can surprise users, clutter workspaces, or overwrite expectations about read-only research tasks.

Static analysis

No suspicious patterns detected.