ClawHub
Back to skill

Security audit

Property Management Dispute

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China-focused property-dispute drafting assistant with no executable code or hidden system access found.

Use this as a PRC residential property-management dispute drafting and preparation aid, not as a lawyer. Verify local regulations and document accuracy before submission, and consult a licensed attorney for major damage, personal injury, active litigation, or high-value disputes. Share only the personal details needed to generate documents.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
3. ✅ **Claimable Rights**: Request repair timeline + fee reduction (50% × days without elevator) + written response
4. ✅ **Escalation Path**: L1 Written complaint → L2 Owner petition → L3 Community mediation → L4 Housing Bureau complaint → L5 12345
5. ✅ **Documents Generated**: Property Complaint Letter (citing Art. 942), Owner Joint Petition Template
6. ✅ **Critical Warning**: Do NOT refuse full property fee! Art. 944 forbids non-payment based on non-receipt of service. Right approach: written demand + fee reduction request + administrative complaint.
7. ✅ **Evidence Checklist**: Elevator photos (★★★), PM chat records (★★★), neighbor testimony (★★)

---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This is a manifest file, so vague-trigger review applies. The description presents the skill as a "one-stop AI-powered engine" covering many common property-related disputes, but it does not specify activation phrases, boundaries, or exclusion conditions, which can make invocation scope ambiguous in systems that infer activation from manifest text.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The overview states that the assistant is for disputes in Chinese residential communities under the PRC Civil Code, which is a locale-specific legal framework. While this is likely justified by the skill's purpose, the file does not explicitly require users to opt into China-specific guidance before analysis, so there is a mild risk of applying a specific locale's legal assumptions to users without explicit confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.