Back to skill

Security audit

胡田-OPC导师-合同风险审查

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent contract-review prompt skill with no executable code or hidden access, but users should treat its legal-risk output as preliminary guidance only.

Install only if you want Chinese-language preliminary contract risk screening. Do not rely on it as final legal advice, especially for material contracts, disputes, regulated sectors, cross-border issues, or significant financial exposure; have a qualified lawyer review those matters.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill presents contract-risk analysis as a practical review tool for non-lawyers but does not warn that its output is informational and not a substitute for qualified legal advice. Because contracts can create binding legal obligations, users may over-rely on the tool and make harmful signing, negotiation, or dispute decisions based on incomplete or inaccurate analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to activate on many general contract-related requests, which can cause the skill to engage outside a clearly defined scope. In a legal-adjacent skill, this increases the chance users receive overconfident, quasi-legal guidance without appropriate boundaries, disclaimers, or escalation to qualified counsel.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

All user-facing description, triggers, and output expectations are presented only in Chinese, and the file does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-language audience. This can violate language or locale policy when a skill implicitly forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.