ClawHub
Back to skill

Security audit

Skillboss

Security checks for vulnerabilities and agentic risk

Overview

SkillBoss is a coherent API wrapper, but it exposes broad third-party model routing plus email and SMS sending without clear safety controls or data-handling warnings.

Review before installing if you plan to use it with private or regulated data, or if your agent may invoke email/SMS tools. Treat prompts, files, audio, and generated content as leaving your environment, and require explicit user approval before any email, SMS, OTP, or batch messaging action.

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 (7)

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The script makes outbound network requests to a third-party API, but the finding indicates network capability is not declared in permissions. In a skill ecosystem this is security-relevant because undeclared egress can transmit prompts, user data, and metadata to external services without the normal transparency or policy checks expected for networked skills.

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The script makes outbound network requests to a third-party API, but the finding indicates network capability is not declared in permissions. In a skill ecosystem this is security-relevant because undeclared egress can transmit prompts, user data, and metadata to external services without the normal transparency or policy checks expected for networked skills.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises broad access to many third-party AI and tool providers but does not warn that user prompts, documents, audio, and other content may be transmitted to external services. This can mislead users into sharing sensitive data under the assumption processing is local or limited to one provider, creating privacy, confidentiality, and compliance risks.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill includes email and SMS capabilities but does not disclose that it can trigger outbound communications or affect user data. Without explicit warnings and guardrails, an agent or user could invoke messaging features unexpectedly, causing data leakage, spam, unwanted charges, or unauthorized external contact.

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 file documents outbound email and SMS capabilities, including batch messaging, without any warning about privacy, consent, billing, or abuse risk. In an agent skill marketed as a broad 'Swiss-knife' for automation, this omission can lead downstream agents or users to invoke high-impact communication tools without realizing they trigger real external actions affecting recipients and potentially regulated personal data.

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
The description "Chinese optimized (fast)" introduces a locale/language-specific constraint in natural language, but the file does not indicate that this model should only be selected with user opt-in or in a region-specific context. Under the policy, forcing or steering toward a specific language/locale without choice or justification is a natural-language policy concern.

Static analysis

No suspicious patterns detected.