ClawHub
Back to skill

Security audit

tialink-tia-portal

Security checks for vulnerabilities and agentic risk

Overview

This skill provides clearly disclosed PLC engineering access with simulation defaults and human approval requirements for real equipment.

Start with a scratch project and simulation, export backups, and retain operator control over production changes. Prefer direct HTTP or a reviewed, pinned adapter version. Keep the gateway private, encrypt remote connections, and protect its token. The separately downloaded gateway and helper executables were not verified by this artifact review.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

MCP server referenced without pinned version: 'npx tialink-mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The adapter is invoked through npx without a pinned package version, allowing newly resolved upstream releases to execute with the client's privileges. A compromised release could steal the supplied gateway token or modify accessible PLC projects; the industrial engineering context increases the potential consequences, although no malicious package behavior is demonstrated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx tialink-mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The smoke-test command runs an unpinned npm package while supplying the gateway credential through the environment. The --check argument does not sandbox package execution, so a compromised upstream release could access that credential and the client's files even when the intended operation is only diagnostic.

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 · SKILL.md (reported line 202)May include surrounding context.

text

```bash
# 没有 Node：curl 也行
curl -sS -X POST "http://127.0.0.1:8080/mcp" \
  -H "Authorization: Bearer <你的令牌>" \
  -H "Content-Type: application/json" \

MCP server referenced without pinned version: 'npx tialink-mcp'.

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The distribution table repeats an unpinned npx invocation, reinforcing the same supply-chain exposure as the executable setup examples rather than introducing a separate attack path. If followed, it can execute a newly published package release on a machine involved in PLC engineering, where credential theft or project tampering could have significant consequences.

Content

No source excerpt is available for this finding.