Back to skill

Security audit

AI电商模特换脸 | AI换脸 | 替换模特 | 换脸工具 | LinkPix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkPix/qhkit workflow for model face replacement, with expected external uploads and setup steps, but users should review consent, region, and installation implications.

Install only if you intend to use qhkit/iqinghu for model face replacement. Confirm rights to any real person's likeness, avoid unauthorized face swaps, review where media will be processed, and consider pinning the npm package version or avoiding persistent PATH changes in controlled environments.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill declares broad, mandatory trigger conditions for common requests like face swap, model replacement, localization, and person replacement. Overbroad forced invocation can cause the agent to route ordinary image-editing requests into a powerful external tool unnecessarily, increasing the chance of privacy-sensitive processing, policy bypass attempts, or accidental misuse.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs fallback execution via npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to be fetched and run. This weakens supply-chain integrity and reproducibility; if the upstream package is compromised or a breaking release is published, the agent may execute unreviewed code.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicated finding points to the same behavior: extracting Node into a user-controlled directory and altering PATH, with optional persistence into ~/.bashrc. That pattern enables durable modification of the agent's runtime environment and increases risk of uncontrolled software execution in later sessions.

Content

Scanner excerpt · SKILL.md (reported line 58)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
88% confidence
Finding

This duplicated finding points to the same behavior: extracting Node into a user-controlled directory and altering PATH, with optional persistence into ~/.bashrc. That pattern enables durable modification of the agent's runtime environment and increases risk of uncontrolled software execution in later sessions.

Content

Scanner excerpt · SKILL.md (reported line 58)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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill hardcodes domestic CN-site/account guidance and effectively steers users toward a specific regional service configuration without explicit user opt-in. This can create privacy, compliance, and data-residency risk if user media or credentials are sent to a jurisdiction or service variant the user did not choose.

Content

No source excerpt is available for this finding.