Security audit

Cheapest Image

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent EvoLink image-generation skill, but it needs Review because it downloads API-returned URLs without destination or size limits.

Install only if you are comfortable sending image prompts to EvoLink with your API key and saving generated files locally. Avoid sensitive prompts, protect the EVOLINK_API_KEY value, and be aware that the current download logic trusts the provider-returned result URL and may download large or unexpected content.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/generate.py:41
Finding: Unvalidated API-Supplied Image URL in Python Implementation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: references/powershell.md:102
Finding: Unvalidated API-Supplied Image URL in PowerShell Fallback
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: references/curl_heredoc.md:43
Finding: Unvalidated API-Supplied Image URL in curl Fallback
Content: View full analysis
Remediation: View remediation

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 (7)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill requires both environment access to read EVOLINK_API_KEY and network access to call the EvoLink API, but it does not explicitly declare a tool scope such as permissions or allowed-tools. That omission weakens least-privilege controls and makes it harder for a host agent or reviewer to understand and constrain what the skill is allowed to access before execution.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example instructs users to send their API key and prompt content to a third-party service and later write the returned image to disk, but it does not clearly warn about those privacy and data-handling consequences. In a skill context, omission of this disclosure can cause users to unknowingly transmit sensitive prompts or credentials and persist generated content locally.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% 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 · references/curl_heredoc.md (reported line 16)May include surrounding context.
md
API_KEY="<API_KEY>" OUT_FILE="<OUTPUT_FILE>" RESP=$(curl -s -X POST "https://api.evolink.ai/v1/images/generations" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d @- <<'EVOLINK_END'

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% 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 · references/curl_heredoc.md (reported line 16)May include surrounding context.
md
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"

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% 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 · references/curl_heredoc.md (reported line 39)May include surrounding context.
md
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"

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% 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 · references/powershell.md (reported line 41)May include surrounding context.
md
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"

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% 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 · scripts/generate.py (reported line 16)May include surrounding context.
python
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"

Static analysis

No suspicious patterns detected.