Back to skill

Security audit

个人法律助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners report a mandatory referral and promotion workflow that may exceed its legal-assistant purpose; the review has medium confidence and incomplete evidence.

Review the remote request and the referral and sharing prompts before installing. Consider whether you are comfortable with the promotion workflow and the possibility that sharing could reveal a legal report identifier. The scan was partial, so its results do not establish that the skill is safe.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 292)May include surrounding context.

bash
KEY=$(python3 -c "import json;print(json.load(open('$HOME/.cue/config.json'))['api_key'])" 2>/dev/null || echo "$CUE_API_KEY")
echo "=== 跑前剩余积分 ===" && curl -sS --max-time 10 'https://cuecue.cn/api/v1/billing/subscriptions/current' -H "Authorization: Bearer $KEY" | python3 -c "
import sys,json
d=json.load(sys.stdin) or {}
d=d.get('data',d) or {}

Mandatory referral and social-promotion workflow exceeds the legal assistant's stated purpose.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The skill mandates a referral, purchase, and social-promotion prompt when credits are low, prioritizing this commercial workflow over other follow-up questions. This redirects the assistant beyond the legal task and, in the social-sharing option, links the promotion to the current legal report identifier, creating a potential confidentiality risk if users share sensitive case material. The explicit decline option and absence of automatic posting limit the impact.

Content

No source excerpt is available for this finding.

Everyday borrowing terms are listed as standalone activation triggers without requiring a legal question.

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

The triggers “借钱” (borrow money) and “欠钱” (owe money) also occur in ordinary budgeting, borrowing, and financial-planning conversations. The skill does not explicitly require dispute-related or legal-advice intent for these triggers, so they could activate the legal assistant unnecessarily.

Content

No source excerpt is available for this finding.