ClawHub
Back to skill

Security audit

Agent Team Orchestration

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only playbook for coordinating agent teams; it has no hidden executable behavior, but users should be mindful of shared workspaces and the external model API it recommends.

Install this if you want a playbook for coordinating multiple agents. Keep API keys out of prompts and shared folders, avoid placing secrets or regulated data in shared artifacts, review persistent agent instruction files before use, and only enable scheduled agents with clear ownership and a way to stop them.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Confidence
91% confidence
Finding
This is a markdown file, so SQP-2 applies to missing warnings in the skill description. Line L027 instructs users to send requests to an external endpoint and use `SKILLBOSS_API_KEY`, but the document does not warn that data will be sent off-system or that credentials are required and should be handled carefully.

External Transmission

Medium
Category
Data Exfiltration
Content
## Model Selection Per Role

Match model cost to the cognitive demands of the role. All models are accessed via SkillBoss API Hub — use `POST https://api.heybossai.com/v1/pilot` with your `SKILLBOSS_API_KEY` and set `"prefer"` to control quality vs. cost tradeoff.

| Role | Needs | Model tier |
|------|-------|-----------|
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.