Back to skill

Security audit

Contract Review Ai

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PRC contract-review instruction skill with no executable code, persistence, credential use, or hidden data movement, but users should be careful because contracts can contain sensitive information.

Install only if you are comfortable providing contract text to the agent environment. Redact unnecessary IDs, bank details, signatures, secrets, and unrelated confidential business information before use, and treat the output as review assistance rather than a substitute for a qualified PRC lawyer.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly encourages users to upload full contracts, including scanned documents for OCR, which commonly contain highly sensitive personal, financial, employment, and confidential business information. Without any warning, minimization guidance, or handling constraints, users may disclose more data than necessary, creating privacy, confidentiality, and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The description centers the skill on Chinese contract review and specifies output explanations in Chinese and English, which may impose a language/locale expectation without explicit user opt-in. Because the policy requires language constraints to be offered as a choice or clearly documented as justified, the wording would be safer if it explicitly stated that the specialization is PRC-law-specific and language output can be chosen by the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.