Pub Mcporter

• Outcome: Review
• Latest audit: Sep 11, 2026 · 8:45 PM UTC
• Version: 1.0.0

Overview

The skill is a broad third-party API gateway that is mostly disclosed, but it includes sensitive data processing plus outbound email and SMS actions without clear user confirmation or privacy controls.

Review this skill carefully before installing. Use it only if you trust SkillBoss/HeyBossAI with the prompts, documents, audio, images, phone numbers, and messages you provide, and require explicit user approval before sending any email, SMS, OTP, or sensitive file/audio/document request.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (31)

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The skill includes email sending and SMS verification capabilities that can contact external recipients, but it provides no safety warning, consent requirement, or confirmation step. This is dangerous because an agent could be induced to send messages or OTP workflows to unintended targets, causing spam, phishing, privacy violations, or operational abuse.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill advertises broad use of external AI, search, document, email, and SMS services but does not warn that prompts, documents, audio, phone numbers, and other user data will be transmitted to a third-party API and potentially onward to multiple providers. This creates meaningful privacy, compliance, and consent risk because users may unknowingly send sensitive data off-platform.

External Transmission

Medium

• Category: Data Exfiltration

Content

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

**Base URL:** `https://api.heybossai.com/v1`
**Auth:** `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`

## List Models

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

**Base URL:** `https://api.heybossai.com/v1`
**Auth:** `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`

## List Models

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

**Base URL:** `https://api.heybossai.com/v1`
**Auth:** `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`

## List Models

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

**Base URL:** `https://api.heybossai.com/v1`
**Auth:** `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`

## List Models

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

**Base URL:** `https://api.heybossai.com/v1`
**Auth:** `-H "Authorization: Bearer $SKILLBOSS_API_KEY"`

## List Models

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

## List Models

```bash
curl -s https://api.heybossai.com/v1/models \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY"
```

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Chat

```bash
curl -s -X POST https://api.heybossai.com/v1/chat/completions \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 92% confidence
• Finding: Chat completions send user messages and optional system prompts to external providers, which can include sensitive text or business information. Because the skill encourages direct use without prominent warnings, users may unintentionally disclose confidential content.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Image Generation

```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: This duplicate URL-level finding maps to the image-generation API call, which sends prompts externally and can expose sensitive content. In context, the lack of user-facing disclosure makes the transmission meaningfully risky.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Image Generation

```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: This duplicate URL-level finding maps to the image-generation API call, which sends prompts externally and can expose sensitive content. In context, the lack of user-facing disclosure makes the transmission meaningfully risky.

External Transmission

Medium

• Category: Data Exfiltration

Content

Save to file:

```bash
URL=$(curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/img", "inputs": {"prompt": "A sunset over mountains"}}' \

• Confidence: 91% confidence
• Finding: The save-to-file flow first sends a prompt externally and then downloads a returned URL, creating both outbound disclosure and follow-up retrieval from remote content. This increases exposure because user content leaves the environment and untrusted remote resources may then be fetched.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Video Generation

```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: This duplicate URL-level finding corresponds to the video-generation API call that transmits prompt content externally. The transmission is expected functionality, but still a real privacy/security concern without consent and warning mechanisms.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Video Generation

```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: This duplicate URL-level finding corresponds to the video-generation API call that transmits prompt content externally. The transmission is expected functionality, but still a real privacy/security concern without consent and warning mechanisms.

External Transmission

Medium

• Category: Data Exfiltration

Content

Image-to-video:

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

• Confidence: 93% confidence
• Finding: The image-to-video example sends both prompt text and a source image URL to a third-party provider, potentially exposing personal or proprietary imagery. That makes this more sensitive than a plain metadata query and warrants stronger safeguards.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Text-to-Speech

```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: This URL-level finding maps to the TTS request, which transmits user text to an external provider. The capability is legitimate, but absent disclosure it creates accidental data-sharing risk.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Text-to-Speech

```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: This URL-level finding maps to the TTS request, which transmits user text to an external provider. The capability is legitimate, but absent disclosure it creates accidental data-sharing risk.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Speech-to-Text

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

• Confidence: 94% confidence
• Finding: This duplicate URL-level finding corresponds to the STT request that uploads audio externally for transcription. Audio can contain highly sensitive information, so the missing warning and consent controls make the issue material.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Speech-to-Text

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

• Confidence: 94% confidence
• Finding: This duplicate URL-level finding corresponds to the STT request that uploads audio externally for transcription. Audio can contain highly sensitive information, so the missing warning and consent controls make the issue material.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Music Generation

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

• Confidence: 89% confidence
• Finding: Music-generation requests send prompts externally and may reveal user content or internal creative material. While lower risk than email or audio transcription, it still involves undisclosed third-party prompt transmission.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Background Removal

```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: This duplicate URL-level finding corresponds to remote image processing for background removal, which can expose sensitive image content to a third party. The absence of warnings keeps this as a valid privacy-related issue.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Background Removal

```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: This duplicate URL-level finding corresponds to remote image processing for background removal, which can expose sensitive image content to a third party. The absence of warnings keeps this as a valid privacy-related issue.

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: 96% confidence
• Finding: Document-processing requests send document URLs to an external parser/extractor, potentially exposing contracts, internal reports, or personal records. This is particularly sensitive because documents often contain dense confidential data and the skill gives no corresponding caution.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Web Search

```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: This duplicate URL-level finding maps to external web search/scraping, which can leak sensitive investigative queries or business context. The risk is moderate and stems from undisclosed third-party processing rather than hidden malicious behavior.

External Transmission

Medium

• Category: Data Exfiltration

Content

## Web Search

```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: This duplicate URL-level finding maps to external web search/scraping, which can leak sensitive investigative queries or business context. The risk is moderate and stems from undisclosed third-party processing rather than hidden malicious behavior.

Static analysis

No suspicious patterns detected.