Security audit

contract-clause-check

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a simple local contract-clause checker, but its documentation and declared tool authority are inconsistent enough that users should review it before installing.

Install only if you are comfortable reviewing Chinese-language contract text locally and can constrain the agent to the provided contract content. Before use, the publisher should align the CLI documentation with the actual --text argument and remove or justify broad tools such as Write and WebFetch.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The skill description presents the domain and core value proposition primarily in Chinese and labels the domain as '法律', while the English line still retains untranslated Chinese text. This can create a language/locale accessibility issue because the skill does not explicitly offer users a language preference or state that it is intended only for Chinese-language legal contracts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The primary manifest description is written in Chinese and states the applicable usage scenario in Chinese only, which can impose a language expectation on users without explicit opt-in. Although the file contains bilingual sections later, the activation/description field itself does not offer a language choice or state that either language is acceptable.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill documentation says users can pass a contract file path via --input, but the declared interface only defines a text string and the permissions deny filesystem access. This mismatch can cause integrators or agents to invoke the skill in an unsafe or noncompliant way, potentially leading to unintended file handling assumptions, policy bypass attempts, or broken security controls around sensitive contract data.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The Chinese usage section repeats that a contract file path may be supplied, which conflicts with both the text-only input schema and filesystem=false permission declaration. In a security-sensitive review workflow, this inconsistency increases the chance of incorrect orchestration, accidental exposure of local files, or attempts to grant broader access than intended.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The natural-language content in this file is entirely in Chinese, including the operational description and file guidance, with no indication that users may choose another language or that the skill is limited to a Chinese-language context. This can violate a language/locale policy when the skill imposes a specific language without opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The script's user-facing description, help text, keywords, and printed results are all hard-coded in Chinese, which imposes a specific language/locale on users. There is no opt-in, fallback, or documentation indicating that the tool is intentionally limited to Chinese-language contracts only.
Content: No source excerpt is available for this finding.