Back to skill

Security audit

buyer-hw-sw-contract-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language buyer-side contract review workflow that may generate a DOCX redline, with no evidence of hidden execution, persistence, exfiltration, or unrelated authority.

Before installing, users should understand that the skill applies Chinese buyer-side commercial defaults, including specific VAT invoice and payment rules, and that full review or revision requests are expected to produce a new DOCX redline containing contract text. Use it with appropriately authorized contract materials and confirm output filename/location if overwrite avoidance 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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and the rest of the skill instructions are written as mandatory Chinese-language workflow/output guidance, including fixed Chinese output structures and terminology. There is no indication that the user may choose another language or that the Chinese-only constraint is explicitly justified as a region-specific policy requirement.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly promises delivery of a revised .DOCX with tracked changes, which implies creating or modifying a user file, but the test content does not disclose that side effect or require explicit user confirmation before file generation. In an agent setting, silent file creation/modification can surprise users, overwrite expected outputs, or cause unintended handling of sensitive contract text, especially because procurement contracts often contain confidential commercial information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file uses Chinese for the substantive contact and maintainer information, and does not provide an alternative language or indicate that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

All visible natural-language instructions and test cases are in Chinese, and the file does not indicate that language is optional or limited to a justified region-specific context. Per the policy rule, forcing a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file contains end-user-facing natural language exclusively in Chinese, and there is no statement that the skill is China-specific or that users may choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.