Security audit

文科论文写作

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese academic-writing template skill with no executable code, network behavior, persistence, or credential handling found.

Install only if you want a Chinese-language academic writing assistant. Do not rely solely on its local-only privacy claims unless your OpenClaw or model runtime is actually configured for local processing; review generated academic work for accuracy, citations, and integrity before use.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The privacy policy is only provided in Chinese, which can prevent non-Chinese-speaking users from understanding how their data is handled, what risks exist, and what responsibilities they retain. This is especially problematic because the document makes strong security and compliance claims, so users who cannot read it may rely on the skill without informed consent or accurate understanding.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The README explicitly states the skill supports '中文论文写作', which is a natural-language locale constraint. Under the policy, forcing a specific language without user opt-in should be flagged unless the restriction is clearly documented and justified as region-specific; this file does not provide that justification or an alternative language option.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description explicitly presents the skill as a Chinese liberal-arts paper assistant, and later instructions/examples are consistently Chinese-only. The file does not offer users a language choice or state that the locale restriction is optional, which is a natural-language locale policy concern under the stated rule.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill makes strong privacy and deployment claims such as 'all processing is local,' 'no external API calls,' and 'no data leakage risk,' but those guarantees are not enforceable from the skill text alone. If the hosting agent or runtime sends prompts, references, or generated content to remote models or telemetry systems, users may disclose sensitive academic or personal data under false assumptions of confidentiality.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill display name and description are explicitly Chinese-focused, while the default prompt is written in English and there is no visible statement offering users a language or locale choice. This creates a natural-language locale policy concern because the skill appears to impose language expectations 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: 93% confidence
Finding: The prompt explicitly requires returning only a Chinese title, which imposes a specific language on the user. Under the language/locale policy, this is a violation unless the skill offers a language choice or clearly documents and justifies the locale restriction.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.