ClawHub
Back to skill

Security audit

evidence organizer

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps organize legal evidence and does not show hidden data access, persistence, or unsafe behavior.

Use this for organizing evidence lists, exhibits, and custody notes, but do not rely on it for legal advice or admissibility decisions; review outputs with a qualified attorney before court use.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on many general requests about organizing evidence, which can cause the skill to be invoked in contexts where the user did not explicitly ask for this specialized workflow. In a legal-assistance context, over-triggering is risky because it may steer users into structured evidentiary preparation without clear intent, increasing the chance of inappropriate reliance or disclosure of sensitive case information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad enough to activate this skill during ordinary legal-help conversations without clearly limiting it to evidence organization. In a legal context, overbroad activation can cause the assistant to provide structured case-preparation guidance when the user may have intended general discussion, increasing the risk of unintended legal-assistance behavior and scope creep.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation guidance prominently specifies Chinese trigger phrases like '证据整理' and '怎么组织证据' but does not state that other languages are also supported or that this is a China-specific or Chinese-language-only skill. That can create a locale/language policy issue because it appears to privilege one language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.