ClawHub
Back to skill

Security audit

Skillboss

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad external AI API helper that is mostly transparent, but it includes real email and SMS sending capabilities without clear user-confirmation guardrails.

Review this skill before installing if your agent may act autonomously. Treat it as an external service connector: do not send secrets, private documents, regulated data, phone numbers, or recipient lists unless approved, and require explicit confirmation before any email, SMS, OTP, notification, or batch-send 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
  • 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 (44)

Missing User Warnings

High
Confidence
98% confidence
Finding
The email example provides a ready-to-run outbound send operation without any caution that it will deliver a real message to an external recipient. In agent contexts, this can lead to unauthorized messaging, spam, disclosure of confidential content, or business-process abuse if invoked without explicit consent.

Missing User Warnings

High
Confidence
98% confidence
Finding
The SMS verification instructions trigger real OTP/SMS delivery to phone numbers but omit any warning about billing, user impact, and external side effects. In autonomous workflows, this can cause unauthorized messages, harassment, quota/billing abuse, or unwanted verification attempts against real users.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises email, SMS, document parsing, web search, and many remote AI functions but does not clearly warn that prompts, documents, audio, images, phone numbers, and recipient data will be transmitted to a third-party service. This can cause unintended disclosure of sensitive data or surprise external actions by downstream agents or users who treat the skill as a local capability.

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
## 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
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
## 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
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
## 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
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
## 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
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
## 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
90% confidence
Finding
This duplicate external-transmission finding is more serious because the endpoint sends real email rather than merely processing content remotely. In the absence of safety warnings and confirmation controls, it enables unintended outbound communications and possible data leakage to arbitrary recipients.

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
90% confidence
Finding
This duplicate external-transmission finding is more serious because the endpoint sends real email rather than merely processing content remotely. In the absence of safety warnings and confirmation controls, it enables unintended outbound communications and possible data leakage to arbitrary recipients.

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
This endpoint sends a real OTP/SMS message to a phone number, creating direct external side effects and potential cost. Without warnings or guardrails, an agent could send unauthorized verification messages, abuse billing, or harass users.

External Transmission

Medium
Category
Data Exfiltration
Content
| `huggingface/{org}/{model}` | Any HuggingFace model — dynamic, no pre-registration |

```bash
curl -s -X POST https://api.heybossai.com/v1/chat/completions \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bedrock/claude-4-5-sonnet", "messages": [{"role": "user", "content": "Explain quantum computing"}]}'
Confidence
89% confidence
Finding
The curl example explicitly transmits request content, including user messages, to an external service over the network. External transmission is expected for an API client, but in security terms it is still a real data egress point that becomes risky when documentation does not warn about sensitive-data handling or downstream model-provider routing.

External Transmission

Medium
Category
Data Exfiltration
Content
| `huggingface/{org}/{model}` | Any HuggingFace model — dynamic, no pre-registration |

```bash
curl -s -X POST https://api.heybossai.com/v1/chat/completions \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bedrock/claude-4-5-sonnet", "messages": [{"role": "user", "content": "Explain quantum computing"}]}'
Confidence
89% confidence
Finding
The curl example explicitly transmits request content, including user messages, to an external service over the network. External transmission is expected for an API client, but in security terms it is still a real data egress point that becomes risky when documentation does not warn about sensitive-data handling or downstream model-provider routing.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The example sends user-supplied prompt content to a third-party API endpoint, but the documentation does not warn users that prompts may contain sensitive data and will leave their environment. In an agent skill context, users may paste secrets, personal data, or proprietary content into prompts, so omission of a disclosure warning creates a real privacy and data-governance risk.

External Transmission

Medium
Category
Data Exfiltration
Content
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
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
| `vertex/veo-3.1-fast-generate-preview` | Google Veo 3.1 |

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/t2v", "inputs": {"prompt": "A cat playing with yarn"}}'
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.