ClawHub
Back to skill

Security audit

Pub Discord

Security checks across malware telemetry and agentic risk

Overview

This is labeled as a Discord skill, but the artifacts mainly document a broad SkillBoss API wrapper that can send user data to third-party services and trigger email or SMS actions.

Install only if you want a broad SkillBoss API helper, not a Discord controller. Use a limited SkillBoss API key, avoid submitting secrets or private files/audio/documents, and require explicit approval before any email, SMS, or OTP action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The skill is advertised as Discord control, but the content actually exposes a broad third-party broker API for chat, media generation, document parsing, search, email, and SMS. This scope mismatch is dangerous because it can cause users or policy systems to grant trust, permissions, or data access under false assumptions, enabling unrelated outbound actions and data transfers.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
Email sending and SMS verification are materially unrelated to Discord control and enable direct outbound communications to arbitrary recipients. In a mis-scoped skill, these capabilities increase abuse potential for spam, social engineering, account verification workflows, or unauthorized messaging, especially if users believe they are only authorizing Discord actions.

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
General document processing and web search are outside the stated Discord-control purpose and route user-supplied content or URLs to external services. This broadens the data exposure surface and may lead users to unknowingly transmit private files, prompts, or browsing targets to third-party processors under a misleading skill identity.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation describes sending email and SMS/OTP messages without any warning that these are real outbound communications with side effects. That omission is dangerous because users may trigger messages, verification flows, or charges without informed consent, and attackers could exploit the ambiguity to disguise abusive messaging behavior as routine skill use.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill shows document, search, image, audio, and other requests to external services without clearly warning that prompts, files, URLs, and media may leave the local environment. This creates a meaningful privacy and data-governance risk because users may submit sensitive content believing the skill is only a local or Discord-specific helper.

External Transmission

Medium
Category
Data Exfiltration
Content
## Email

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
88% confidence
Finding
curl -s -X POST https://api.heybossai.com/v1/run \ -H "Authorization: Bearer $SKILLBOSS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "email/send", "inputs": {"to": "us

External Transmission

Medium
Category
Data Exfiltration
Content
## Document Processing

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
84% confidence
Finding
https://api.heybossai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
## Email

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
88% confidence
Finding
https://api.heybossai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
Send OTP:

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
90% confidence
Finding
https://api.heybossai.com/

External Transmission

Medium
Category
Data Exfiltration
Content
Verify OTP:

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
88% confidence
Finding
https://api.heybossai.com/

VirusTotal

No VirusTotal findings

View on VirusTotal

Static analysis

No suspicious patterns detected.