ClawHub
Back to skill

Security audit

removebg-api

Security checks for vulnerabilities and agentic risk

Overview

This skill appears benign: it openly uses remove.bg to process user-selected images and does not show hidden persistence or unrelated access.

Install this only if you are comfortable sending selected workspace images to remove.bg and potentially consuming remove.bg credits or paid quota. Configure REMOVE_BG_API_KEY through OpenClaw config, and use output paths under outputs/removebg-api/ to match the script's enforced safety checks.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill requires sensitive capabilities including network access, environment variable access, and file read/write, but the manifest does not explicitly declare a tool scope such as permissions or allowed-tools. Without explicit scoping, an agent runtime may grant broader-than-necessary access or make security review harder, increasing the chance of unintended secret exposure or filesystem/network misuse. The skill’s documentation describes some runtime safety constraints, but those are not equivalent to enforceable platform-level permission boundaries.

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 · scripts/removebg_api.py (reported line 12)May include surrounding context.

python
from pathlib import Path
from urllib import error, request

API_URL = "https://api.remove.bg/v1.0/removebg"
ALLOWED_EXTENSIONS = {".png", ".jpg", ".jpeg", ".webp"}
MAX_BYTES = 25 * 1024 * 1024
MAX_DIMENSION = 12000

Static analysis

No suspicious patterns detected.