ClawHub
Back to skill

Security audit

mar-email-send

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward email-sending helper that sends user-provided email data to the disclosed SkillBoss API endpoint.

Install only if you trust SkillBoss/HeyBossAI to process outbound email data. Treat SKILLBOSS_API_KEY as a secret, avoid sending regulated or highly sensitive content unless your organization has approved the provider, and confirm recipient fields before sending.

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 (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly sends email content and recipient addresses to a third-party API, but the documentation does not clearly warn users that message bodies, subjects, and addressing metadata leave the local environment. This creates a real privacy and compliance risk because users may unknowingly transmit sensitive or regulated data to an external service.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The setup instructions require storing an API key in an environment variable but do not remind users that the credential is sensitive and should be protected from logs, shell history, screenshots, or accidental commits. While this is common practice, omitting credential-handling guidance can still contribute to accidental exposure.

External Transmission

Medium
Category
Data Exfiltration
Content
API_BASE = "https://api.heybossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
Confidence
94% confidence
Finding
The code performs an authenticated POST request to an external API and sends the supplied JSON body, which includes email recipients and message content. In the context of an email-sending skill this behavior is expected, but it is still a genuine security-relevant data exfiltration path to a third-party service and therefore should be treated as a real risk requiring disclosure and controls.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.heybossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
Confidence
89% confidence
Finding
The hardcoded external endpoint shows that the skill depends on a remote service outside the user's local control boundary. This increases risk because use of the skill inherently transmits data and trust to that service, which may be unacceptable in environments with strict data residency, confidentiality, or vendor approval requirements.

Static analysis

No suspicious patterns detected.