ClawHub
Back to skill

Security audit

ai-image-generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-generation API helper, with the main caution that prompts and image URLs are sent to SkillBoss API Hub.

Install this only if you are comfortable using SkillBoss API Hub and sending image prompts, generation settings, and any provided image URLs to that service. Avoid submitting secrets, private images, regulated data, or confidential business material unless your organization permits that provider and data flow.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is extremely broad and includes many generic phrases like 'image generation', 'ai art', and 'generate image', which can cause the skill to activate for a wide range of ordinary user requests. In an agent environment, overbroad activation increases the chance that user prompts, including sensitive business content or private images, are routed to this third-party API without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill demonstrates sending user-supplied prompts and image URLs directly to an external API but does not clearly warn that this data leaves the local agent environment. Because image prompts and source image URLs may contain sensitive personal, proprietary, or regulated content, this omission creates a meaningful privacy and data-governance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.heybossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The code performs an authenticated POST request to an external service and forwards the full request body, which includes user prompts and potentially image URLs. In the context of an agent skill, external transmission is security-relevant because users may not realize their content is being sent off-platform, and the bearer token also creates dependency on secure secret handling and trusted third-party processing.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
API_BASE = "https://api.heybossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Several instructional sections and labels are written in Chinese, including headings and comments such as "自动路由至最优图像生成模型," "Discover 模式," and "环境变量," while the rest of the skill is in English. This imposes a locale/language assumption without offering the user a language choice or justifying the constraint as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.