ClawHub
Back to skill

Security audit

Best Image

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends prompts to EvoLink to generate images and saves the result locally, with no hidden persistence or unrelated behavior found.

Install only if you intend to use EvoLink for image generation. Prompts, generation settings, and any reference image URLs are sent to EvoLink using your API key, generated images are saved locally, and usage may create API charges, especially for higher quality settings.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill invokes code that requires environment access and outbound network access, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a transparency and policy-enforcement gap: an agent or user may authorize or run the skill without clearly understanding that it can consume a secret API key and make external API calls.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The trigger section instructs the agent to generate images immediately from natural-language patterns, but it does not place an equally prominent warning there that execution will create local files and may incur paid API usage. In an agent setting, this can lead to unintended automatic actions, surprise charges, and disk writes from what looks like a simple conversational phrase.

External Transmission

Medium
Category
Data Exfiltration
Content
# curl + heredoc (Unix/macOS only, no dependencies)

> **Note**: This uses bash heredoc syntax which does not work on Windows (cmd/PowerShell). For Windows without Python, see `references/powershell.md` instead.
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlparse


API_BASE = "https://api.evolink.ai/v1"
_UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlparse


API_BASE = "https://api.evolink.ai/v1"
_UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlparse


API_BASE = "https://api.evolink.ai/v1"
_UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlparse


API_BASE = "https://api.evolink.ai/v1"
_UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
Confidence
60% 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

Low
Confidence
83% confidence
Finding
This markdown file includes a curl POST request to api.evolink.ai using a bearer token and user-supplied prompt content, but the surrounding instructions do not explicitly warn that user data and credentials are being sent to a third-party API. For markdown files, user-facing documentation should disclose behaviors that may affect privacy or external data sharing.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The script writes downloaded image content to a local path, which is a filesystem-modifying operation. Although an --out argument exists and the behavior is implied by the tool's purpose, there is no explicit user-facing disclosure at the write site unless verbose mode is enabled.

Missing User Warnings

Low
Confidence
91% confidence
Finding
This code sends the user's prompt, quality/size selections, and any provided reference image URLs to a remote API endpoint. While the script's purpose is image generation, there is no runtime print, confirmation, or comment near the request that explicitly discloses that user-supplied content is transmitted off-system.

Static analysis

No suspicious patterns detected.