Back to skill

Security audit

图片去水印 | 去除水印 | 水印移除 | 去LOGO | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed image watermark-removal integration that uses an external Qinghu/qhkit service, with some normal installation and credential risks users should understand.

Install only if you are comfortable using the Qinghu/qhkit service, providing its API token, uploading the target image to that service, and installing npm/Node tooling. Confirm the estimate before generation because credits may be charged, and use the skill only on images you own or are authorized to modify.

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
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill 'must trigger' whenever a user wants to remove watermarks, logos, text, or marks from an image, and then lists broad keyword-style terms. While domain-related, these activation conditions are not bounded by explicit exclusions or negative examples, which could cause unintended invocation for adjacent image-editing requests.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at install time. That creates supply-chain risk: a malicious or compromised future release could be fetched and run automatically in the agent environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
82% confidence
Finding

This duplicate finding points to the same behavior: unpacking downloaded binaries into a user-controlled persistent directory and exporting that location into PATH. Even though the text recommends checksum verification, the persistence aspect still leaves additional software resident for future execution contexts.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
82% confidence
Finding

This duplicate finding points to the same behavior: unpacking downloaded binaries into a user-controlled persistent directory and exporting that location into PATH. Even though the text recommends checksum verification, the persistence aspect still leaves additional software resident for future execution contexts.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The '何时触发' section provides a few positive examples but does not define boundaries for when the skill should not be invoked. Without exclusions or a complete trigger scope, similar everyday requests about editing images or removing text could overlap and activate the skill unintentionally.

Content

No source excerpt is available for this finding.