Security audit

Wiki Framework Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill generates Chinese consulting-style report frameworks and a Word document from a scoped research brief, with no evidence of hidden data access, persistence, exfiltration, or destructive behavior.

Install this if you want Chinese consulting or government-style report framework generation from a scope.json handoff. Confirm language expectations first if your workflow requires English or bilingual deliverables, and run the DOCX script only on handoff JSON files you intend to convert.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill instructs the agent to read local reference files such as references/engineering_dimension_database.md, references/framework_generation_rules.md, and references/external_framework_standard.md, but it does not declare any explicit tool scope or permissions. Undeclared file access weakens least-privilege controls and can allow broader-than-expected workspace reads if the runtime interprets file capabilities permissively.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The instruction 输出语言固定为中文 forces Chinese output regardless of user preference or upstream context. This can override user intent, reduce transparency for reviewers, and in multilingual workflows may cause misinterpretation of security-relevant or contractual content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file content is presented entirely in Chinese with no indication that users may choose another language or locale. This can violate a language/locale policy when a skill or reference material implicitly requires one language without offering opt-in or alternatives.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document requires section titles and numbering in Chinese formats such as 目录, 第一节/第一章, and 一、二、三, which imposes a specific language/locale convention. The file does not indicate this is optional, user-selected, or limited to a clearly justified region-specific workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The style section instructs use of a report framework and explicitly prefers 第一节/第一章 + 一、二、三 for reports, reinforcing a Chinese-only output convention. Because the file is framed as an external framework standard and not clearly scoped to a China-specific audience, this can violate language/locale policy by forcing a locale without user choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This file contains core routing and framework-generation guidance in Chinese, which effectively forces a specific language/locale for users reading or invoking the skill behavior. Under the policy, language constraints should either be optional for the user or clearly documented as region-specific and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The required chat summary fields are specified in Chinese and line L011 explicitly requires unknown items to be marked as “待确认,” which imposes a specific language convention. The file does not indicate that the user may choose another language or that the Chinese-only requirement is justified by a region-specific use case.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description is entirely in Chinese and specifies output artifacts and behavior in a way that implies the skill operates in that language context, but it does not offer any language choice or explain a required locale constraint. This can violate language/locale policy where skills must not force a specific language without user opt-in or documented justification.
Content: No source excerpt is available for this finding.