ClawHub
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 SkillBoss's external API, with the main caution being that prompts and image URLs leave the local environment.

Install only if you intend to use SkillBoss as an external image-generation provider. Treat prompts, image URLs, and request metadata as data sent to a third party, and avoid submitting secrets, confidential business material, or private image links unless that is acceptable for your use case.

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
97% confidence
Finding

The trigger list includes broad phrases such as 'image generation', 'generate image', and 'generative ai', which are likely to match routine user requests and cause unintended invocation of this external-call skill. Because the skill sends prompts to a third-party API, overbroad activation increases the chance of accidental data disclosure and user confusion about where their content is being processed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation encourages users to submit prompts and image URLs to SkillBoss but does not clearly warn that these inputs are transmitted to an external third-party service. This creates a privacy and consent issue, especially if users provide sensitive prompts, proprietary descriptions, or private image URLs without realizing they leave the local environment.

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 20)May include surrounding context.

md
import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.skillboss.co/v1"

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

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The sample code performs an authenticated POST request to a third-party endpoint and forwards arbitrary request body content, including user prompts and potentially image URLs, to an external service. In the context of an agent skill, this is security-relevant because it can exfiltrate sensitive user data off-platform if invocation and consent controls are weak or unclear.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
API_BASE = "https://api.skillboss.co/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
88% confidence
Finding

Several instructional lines and comments switch to Chinese (for example, model description and response-format guidance) while the rest of the skill is in English, with no indication that the user opted into that language or that the skill is region-specific. This can violate a language/locale policy requiring user choice or clear documentation of locale constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.