ClawHub
Back to skill

Security audit

Gemini

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward remote LLM API skill, but prompts you submit are sent to SkillBoss.

Install only if you are comfortable sending prompts and supplied text to SkillBoss's hosted API. Do not include secrets, private customer data, regulated content, or proprietary material unless your organization has approved that service and its data handling terms.

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 (7)

External Transmission

Medium
Category
Data Exfiltration
Content
---
name: gemini
description: LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub.
homepage: https://api.SkillBoss.co/v1/pilot
metadata: {"clawdbot":{"emoji":"♊️","requires":{"env":["SkillBoss_API_KEY"]}}}
---
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly encourages sending arbitrary user prompts and text to a third-party API but does not clearly warn that prompt contents will leave the local environment and be processed remotely. In a skill context, users may paste sensitive data into examples, so the omission creates a real privacy and data-handling risk even if the transmission is expected functionality.

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.SkillBoss.co/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
94% confidence
Finding
The example sends prompt text and an API bearer token to a remote endpoint over the network. Although this is intentional API usage rather than covert behavior, it is still security-relevant because it exposes user input to a third party and relies on proper handling of the credential.

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.SkillBoss.co/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
94% confidence
Finding
The example sends prompt text and an API bearer token to a remote endpoint over the network. Although this is intentional API usage rather than covert behavior, it is still security-relevant because it exposes user input to a third party and relies on proper handling of the credential.

External Transmission

Medium
Category
Data Exfiltration
Content
def ask(prompt: str, prefer: str = "balanced") -> str:
    r = requests.post(
        "https://api.SkillBoss.co/v1/pilot",
        headers={"Authorization": f"Bearer {SkillBoss_API_KEY}", "Content-Type": "application/json"},
        json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
        timeout=60,
Confidence
95% confidence
Finding
This line identifies the concrete remote endpoint used to process prompts, confirming that user content is sent off-host to a third-party service. In context, this is intended behavior, but it remains a true security/privacy concern because the skill provides no substantive warning or control around transmitted content.

External Transmission

Medium
Category
Data Exfiltration
Content
Quick start (curl)
```bash
curl -s https://api.SkillBoss.co/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
92% confidence
Finding
The curl snippet exposes a straightforward command for sending arbitrary content to the external endpoint, which can lead to unintended disclosure if copied blindly with real data. The danger is amplified slightly by the skill's purpose as a convenience wrapper, making remote transmission easy and implicit.

External Transmission

Medium
Category
Data Exfiltration
Content
Quick start (curl)
```bash
curl -s https://api.SkillBoss.co/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
92% confidence
Finding
The curl snippet exposes a straightforward command for sending arbitrary content to the external endpoint, which can lead to unintended disclosure if copied blindly with real data. The danger is amplified slightly by the skill's purpose as a convenience wrapper, making remote transmission easy and implicit.

Static analysis

No suspicious patterns detected.