ClawHub
Back to skill

Security audit

1.2.0

Security checks for vulnerabilities and agentic risk

Overview

This is a small data-quality operations playbook with templates and harmless echo scripts, with no hidden persistence, credential use, network calls, or destructive behavior found.

Before installing, confirm that the referenced `dq` and `workflow` commands in your environment are the tools you expect and that saving audit artifacts is acceptable for the datasets involved. The bundled files themselves are static and low-risk.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared purpose suggests functionality related to data quality checks and anomaly investigation support. However, the actual code does not implement any validation, checking, anomaly handling, or related resource access; it merely echoes a version identifier. This is a materially different primary purpose, so the description does not accurately represent the code chunk.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared description says the skill provides data quality validation patterns for daily checks and anomaly follow-up. However, the supplied code only echoes a fixed 'ok' message with a skill name and version. It does not validate data, inspect anomalies, process inputs, or implement any daily check logic. This is a materially different primary purpose, so the description does not accurately represent the code chunk.

Static analysis

No suspicious patterns detected.