ClawHub
Back to skill

Security audit

Skillboss

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small remote AI-gateway wrapper that sends prompts and its own API key to a third-party API, with no evidence of hidden persistence or destructive behavior.

Install only if you are comfortable sending prompts and the SKILLBOSS_API_KEY to api.heybossai.com. Avoid pasting secrets, private source code, regulated data, or sensitive business content unless SkillBoss/HeyBossAI's data handling terms are acceptable to you.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding
The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env node

const API_BASE = "https://api.heybossai.com/v1";

function usage() {
  console.error(`Usage: run.mjs <command> [options]
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The run command sends both the user's prompt and the API credential to a third-party service, but the code provides no explicit disclosure at the point of use that user content leaves the local environment. In security-sensitive contexts, users may paste secrets, source code, or proprietary data into prompts without realizing they are being transmitted to an external provider.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
Task mode also transmits user-supplied prompt data and credentials to a remote endpoint, again without explicit warning in the command flow. Because task mode auto-selects models, users may have even less clarity about where their data is going and how it is processed.

Missing User Warnings

Low
Confidence
84% confidence
Finding
Even though this command may not include user prompt text, it still sends a sensitive API credential over the network. The file lacks a comment or user-facing disclosure explaining this remote transmission.

Static analysis

No suspicious patterns detected.