ClawHub
Back to skill

Security audit

七步法法律工作流

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown legal-analysis workflow with no code or hidden system access, though users should treat its legal output as jurisdiction-specific and verify it manually.

Before installing, understand that this skill can structure legal analysis but cannot replace a lawyer’s judgment. Confirm the relevant jurisdiction, provide the exact current statute text, and independently verify any cited cases or legal authorities in official or trusted legal databases.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description claims applicability to 'any statutory case' and presents a complete end-to-end workflow, which is an overly broad activation condition for legal work. In a legal-assistance context, this can cause the agent to engage on matters beyond its validated jurisdiction, subject-matter scope, or risk tolerance, increasing the chance of incorrect or unsafe legal guidance being generated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow hard-codes Chinese legal sources and validation requirements without first confirming that the user's matter is in the PRC legal context. If triggered for another jurisdiction, the skill may anchor analysis to the wrong legal system and authorities, producing materially incorrect legal reasoning or misleading source validation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.