ClawHub
Back to skill

Security audit

meme-maker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed meme-generation tool; it uses Imgflip network calls and optional Imgflip credentials for expected hosted rendering, with no hidden persistence or unrelated behavior found.

Install only if you are comfortable with Imgflip network access. Use the default local mode when you do not want meme text sent to a hosted service, avoid putting sensitive text in meme captions, and prefer environment variables over command-line password flags where process-list exposure matters.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documentation describes network access, environment-variable use, and executable code paths, but the manifest does not declare any explicit tool scope or permissions boundaries. This creates a capability mismatch where a host may permit broader access than users expect, increasing the risk of unintended outbound requests, credential use, or data exposure during meme rendering and template fetching.

External Transmission

Medium
Category
Data Exfiltration
Content
const BASE_DIR = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
const TEMPLATES_PATH = path.join(BASE_DIR, "references", "templates.json");
const IMGFLIP_GET_MEMES_URL = "https://api.imgflip.com/get_memes";
const IMGFLIP_CAPTION_URL = "https://api.imgflip.com/caption_image";
const USER_AGENT = "OpenClawMemeMaker/1.0";
const STOPWORDS = new Set([
Confidence
50% 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
const BASE_DIR = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
const TEMPLATES_PATH = path.join(BASE_DIR, "references", "templates.json");
const IMGFLIP_GET_MEMES_URL = "https://api.imgflip.com/get_memes";
const IMGFLIP_CAPTION_URL = "https://api.imgflip.com/caption_image";
const USER_AGENT = "OpenClawMemeMaker/1.0";
const STOPWORDS = new Set([
  "a",
Confidence
85% confidence
Finding
The caption_image endpoint sends user-provided meme text and Imgflip credentials to a third-party service, which is a real data-transmission risk even if intended functionality. In this skill context, the danger is moderate because render operations may disclose secrets entered on the command line or in environment variables to an external service, and users may not expect hosted generation to transmit content off-host.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/meme.mjs:145