Back to skill

Security audit

Ai Image Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-generation helper that uses a disclosed third-party API and does not show hidden execution, persistence, or destructive behavior.

Install only if you are comfortable sending image prompts, image URLs, and related generation settings to SkillBoss API Hub using your SKILLBOSS_API_KEY. Avoid submitting secrets, private internal URLs, confidential source images, or sensitive personal data unless your policy permits that provider.

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
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 manifest description includes a very large set of broad trigger phrases such as 'image generation', 'generate image', 'ai art', and 'generative ai', which can cause the skill to activate in situations broader than users may expect. Over-broad routing is risky because it can send user prompts and related content to this skill and then onward to a third-party API without sufficiently specific intent from the user.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill sends prompts and possibly image URLs to the external SkillBoss API, but the user-facing description and quick-start section do not clearly warn that user content is transmitted to a third-party service. This creates a privacy and consent issue because users may unknowingly provide sensitive prompts, proprietary images, or internal URLs to an external provider.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The hardcoded external API base URL establishes that this skill depends on a third-party network service for operation. While using an external API is not inherently malicious, it is a genuine security concern in this context because all downstream requests are directed off-platform, expanding the attack surface and creating privacy, availability, and supply-chain risk.

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

This code performs an authenticated POST request to an external API endpoint and forwards the entire request body, which may include user prompts and image URLs. In the context of an agent skill, external transmission is security-relevant because sensitive user data can leave the local trust boundary and be processed by a third party, especially without explicit minimization, validation, or consent messaging.

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
83% confidence
Finding

Several headings and instructional comments switch from English to Chinese, such as the model description, response format, and environment variable sections. This creates an implicit language constraint for part of the skill documentation without stating that the skill is intended for Chinese-speaking users or offering an alternative language option.

Content

No source excerpt is available for this finding.