ClawHub
Back to skill

Security audit

alv-gemini

Security checks for vulnerabilities and agentic risk

Overview

This is a simple instruction-only skill for sending user prompts to a declared third-party LLM API, with no hidden install, persistence, or unrelated access.

Install only if you trust SkillBoss API Hub and are comfortable sending prompts and supplied text to that service. Use a dedicated, least-privilege API key, and avoid sending secrets, regulated data, or internal-only material unless your policies allow it.

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 (5)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs users to send prompts to a third-party LLM API but does not warn that prompt contents will leave the local environment and be processed by an external service. This can cause inadvertent disclosure of sensitive data, especially in agent settings where prompts may contain private documents, credentials, or internal context.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def ask(prompt: str, prefer: str = "balanced") -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
Confidence
92% confidence
Finding
This code sends user-provided prompt content to an external endpoint, creating a real data exfiltration path from the local agent/runtime to a third-party service. In this skill context, that is the intended functionality, but it is still security-relevant because prompts may contain sensitive or privileged information.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def ask(prompt: str, prefer: str = "balanced") -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
Confidence
92% confidence
Finding
This code sends user-provided prompt content to an external endpoint, creating a real data exfiltration path from the local agent/runtime to a third-party service. In this skill context, that is the intended functionality, but it is still security-relevant because prompts may contain sensitive or privileged information.

External Transmission

Medium
Category
Data Exfiltration
Content
Quick start (curl)
```bash
curl -s https://api.heybossai.com/v1/pilot \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'
Confidence
90% confidence
Finding
The curl example demonstrates transmitting user content directly to a remote LLM API, again creating a channel for sensitive information to leave the local environment. Because this is documentation intended for copy-paste use, the lack of privacy warning increases the chance of unsafe adoption.

External Transmission

Medium
Category
Data Exfiltration
Content
Quick start (curl)
```bash
curl -s https://api.heybossai.com/v1/pilot \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'
Confidence
90% confidence
Finding
The curl example demonstrates transmitting user content directly to a remote LLM API, again creating a channel for sensitive information to leave the local environment. Because this is documentation intended for copy-paste use, the lack of privacy warning increases the chance of unsafe adoption.

Static analysis

No suspicious patterns detected.