Back to skill

Security audit

追加被执行人申请书生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable legal drafting skill with no hidden system access, though users should treat its court document output as a draft requiring legal review.

Install only if you want assistance drafting enforcement-related legal materials. Do not file generated documents without verifying facts, current law, jurisdictional requirements, evidence, and legal strategy with qualified counsel. Treat the self-stated CLEAN and NOT Suspicious labels as publisher claims, not independent guarantees.

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
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly advertises generating a court-submittable legal application document, but provides no warning that the output may be incomplete, jurisdiction-dependent, or require review by a qualified lawyer before filing. In a legal-enforcement context, users may over-rely on the generated document, leading to inaccurate filings, procedural errors, or unsupported claims presented to a court.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes "公司没钱" at L1, which is a broad natural-language phrase that could appear in ordinary discussion rather than a clear invocation command. The manifest does not provide constraints, exclusions, or negative examples to distinguish casual mention from intentional skill activation.

Content

No source excerpt is available for this finding.